© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11949
    Prev
    Next
    INDEX
    Explanations

    conjunctions, especially 'and', in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "and then" or its variations frequently used in a context of adding information or transitioning between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.89
    STE
    -0.79
     Dragonbound
    -0.76
    FL
    -0.71
    Adult
    -0.71
    NSA
    -0.69
    Surv
    -0.65
    76561
    -0.65
    Street
    -0.65
    Initial
    -0.64
    POSITIVE LOGITS
    rogen
    0.93
    rogens
    0.90
     hopefully
    0.80
     consequently
    0.79
     therefore
    0.74
     foremost
    0.74
     secondly
    0.73
     moreover
    0.72
     thus
    0.71
     furthermore
    0.70
    Activations Density 0.134%

    No Known Activations