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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1653
    Prev
    Next
    INDEX
    Explanations

    words expressing a change or transition happening over time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "in."

    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
    hower
    -0.63
    Height
    -0.63
    ername
    -0.62
    Percent
    -0.61
    ctors
    -0.60
     Guilty
    -0.60
    HAEL
    -0.60
    EStreamFrame
    -0.59
    ="#
    -0.59
    AX
    -0.57
    POSITIVE LOGITS
    been
    0.96
    stood
    0.81
    ked
    0.76
    grown
    0.74
    ayed
    0.72
    oured
    0.71
     abundance
    0.70
    umption
    0.67
     been
    0.64
    urred
    0.63
    Activations Density 0.146%

    No Known Activations