Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5979
    Prev
    Next
    INDEX
    Explanations

    instances where a suggestion or alternative course of action is presented

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fla
    -0.81
    ĸļ
    -0.73
    icing
    -0.67
    Raven
    -0.66
    htaking
    -0.63
     Naz
    -0.60
    Hol
    -0.59
    ãĤ£
    -0.58
    hess
    -0.58
    iami
    -0.58
    POSITIVE LOGITS
     goto
    0.89
     nevertheless
    0.83
     forfeit
    0.78
    throw
    0.76
     simply
    0.74
     blame
    0.73
     revert
    0.73
     recourse
    0.72
     alternatively
    0.70
     despair
    0.68
    Activations Density 0.301%

    No Known Activations