© 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. 7-RES-JB
    11. 24204
    Prev
    Next
    INDEX
    Explanations

    features relevant to decision-making and identification of specific attributes or individuals

    oai_token-act-pair · gpt-3.5-turbo

    decisions related to selection and assignment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    krit
    -0.75
    nsic
    -0.67
    actionDate
    -0.67
    İĭ
    -0.66
    =-=-
    -0.66
    conv
    -0.64
    iots
    -0.64
    vity
    -0.64
    legram
    -0.64
    enture
    -0.63
    POSITIVE LOGITS
    heit
    0.84
     versus
    0.68
     priorit
    0.68
     compatible
    0.65
     best
    0.64
     optimal
    0.64
     based
    0.61
     fitt
    0.61
    ribut
    0.60
     eaten
    0.60
    Activations Density 0.316%

    No Known Activations