© 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. 11-RES-JB
    11. 15679
    Prev
    Next
    INDEX
    Explanations

    phrases related to specifying locations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or states related to systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.77
    ode
    -0.71
    AMY
    -0.70
    Others
    -0.69
    english
    -0.64
     Others
    -0.64
    tro
    -0.62
    uc
    -0.62
    incial
    -0.60
    anton
    -0.59
    POSITIVE LOGITS
     whenever
    1.43
     if
    1.31
     whoever
    1.20
     each
    1.13
     unless
    1.09
     when
    1.09
     whichever
    1.08
     every
    1.00
     suppose
    0.97
     unlike
    0.96
    Activations Density 0.320%

    No Known Activations