© 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. 2-RES-JB
    6. 13583
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and terms, particularly people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -0.91
    urity
    -0.86
    atility
    -0.75
    urities
    -0.75
    resa
    -0.74
    thia
    -0.74
    anche
    -0.73
    eus
    -0.72
    mares
    -0.72
    onomy
    -0.71
    POSITIVE LOGITS
     Garc
    0.83
     challeng
    0.78
     garg
    0.77
    ENCY
    0.73
     embr
    0.72
    à©
    0.71
     "$:/
    0.70
    ãĥ¯ãĥ³
    0.68
     targ
    0.68
    rier
    0.67
    Activations Density 0.021%

    No Known Activations