© 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. 19578
    Prev
    Next
    INDEX
    Explanations

    mentions of attributes or actions followed by hyphens

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-description or self-identity

    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
     Springs
    -0.72
    ulhu
    -0.69
     Walls
    -0.68
    Ô
    -0.67
     Butterfly
    -0.64
    stanbul
    -0.63
     seams
    -0.62
     Downs
    -0.62
     Borders
    -0.61
     AVG
    -0.60
    POSITIVE LOGITS
    directed
    0.80
    occupied
    0.76
    friend
    0.73
    aligned
    0.73
    oriented
    0.72
    service
    0.72
    friendly
    0.72
    sized
    0.72
    eating
    0.71
    selves
    0.71
    Activations Density 0.102%

    No Known Activations