© 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. 10-RES-JB
    11. 7989
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hig
    -0.70
    ãĥ´ãĤ¡
    -0.70
    ãĤ´ãĥ³
    -0.70
    probably
    -0.69
    Probably
    -0.67
    undo
    -0.67
    orah
    -0.65
    minus
    -0.64
    rax
    -0.64
    Ô
    -0.63
    POSITIVE LOGITS
     someone
    1.36
     somebody
    1.30
     you
    1.21
    someone
    1.10
     people
    1.06
     individuals
    0.93
     your
    0.93
     consumers
    0.90
     we
    0.87
     something
    0.84
    Activations Density 0.249%

    No Known Activations