© 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. 4-RES-JB
    11. 2806
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive or negative correlation between different variables

    oai_token-act-pair · gpt-3.5-turbo

    correlations and sentiments expressed in relation to positive and negative outcomes

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

    No Comments

    Negative Logits
    iens
    -0.85
     flaws
    -0.72
     horizont
    -0.70
    ador
    -0.69
    Offline
    -0.68
    GER
    -0.67
     Times
    -0.67
     univers
    -0.66
     GOODMAN
    -0.65
     limitations
    -0.64
    POSITIVE LOGITS
     impacting
    1.05
     impacted
    0.94
     charged
    0.92
     effected
    0.87
     affecting
    0.87
     disposed
    0.86
     correlated
    0.86
     detonated
    0.80
     interacted
    0.80
     minded
    0.77
    Activations Density 0.012%

    No Known Activations