© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14835
    Prev
    Next
    INDEX
    Explanations

    details and specific aspects in descriptions or images

    oai_token-act-pair · gpt-3.5-turbo

    references to high levels of detail

    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
    onz
    -0.86
    anski
    -0.75
    rams
    -0.74
    orea
    -0.72
    ammers
    -0.72
    ammy
    -0.70
    arte
    -0.69
    esta
    -0.68
    ento
    -0.68
    mire
    -0.67
    POSITIVE LOGITS
     detail
    1.06
    ariat
    0.81
    iveness
    0.81
     details
    0.81
     Detail
    0.74
    smanship
    0.73
    ured
    0.72
    uring
    0.70
     markings
    0.66
     settings
    0.65
    Activations Density 0.023%

    No Known Activations