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

    Neuronpedia

    Jacobian LensNEW
    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. 12097
    Prev
    Next
    INDEX
    Explanations

    phrases related to settling in or being in a settled state

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a process of settling or establishing oneself in a context

    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
    alf
    -0.74
    WT
    -0.73
    run
    -0.71
    wcs
    -0.71
    endor
    -0.67
    runs
    -0.66
    ell
    -0.64
    vous
    -0.62
    ison
    -0.62
    illary
    -0.62
    POSITIVE LOGITS
     laure
    0.74
     groove
    0.71
     Diseases
    0.68
     footing
    0.68
     midway
    0.65
     Wast
    0.64
    cellence
    0.61
     halfway
    0.60
    onics
    0.59
    ciating
    0.59
    Activations Density 0.122%

    No Known Activations