© 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. 7-RES-JB
    11. 24205
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavioral inclinations or patterns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe behavioral tendencies or inclinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oho
    -0.79
    arer
    -0.79
    mson
    -0.78
    loo
    -0.78
    erial
    -0.73
    estamp
    -0.71
    anmar
    -0.69
    manship
    -0.68
     Tek
    -0.68
    NZ
    -0.67
    POSITIVE LOGITS
     toward
    1.08
     towards
    1.00
     tendency
    0.99
     tendencies
    0.92
    entious
    0.84
     prone
    0.81
     impulse
    0.79
     behaviour
    0.78
     predis
    0.77
     propensity
    0.76
    Activations Density 0.042%

    No Known Activations