© 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. 8-RES-JB
    11. 22688
    Prev
    Next
    INDEX
    Explanations

    phrases related to the influence or shaping of something

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to influence and the shaping of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uters
    -0.77
    aeus
    -0.68
    onds
    -0.66
    sm
    -0.66
    oney
    -0.65
    iolet
    -0.64
    bestos
    -0.64
    ubs
    -0.63
    fml
    -0.63
    iphate
    -0.62
    POSITIVE LOGITS
     perceptions
    0.90
     decisions
    0.81
     shaping
    0.80
     attitudes
    0.77
     our
    0.77
     them
    0.75
     subsequent
    0.75
     future
    0.74
     how
    0.71
     us
    0.71
    Activations Density 0.213%

    No Known Activations