© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8571
    Prev
    Next
    INDEX
    Explanations

    phrases related to levels or amounts, with a focus on extremes or comparisons such as "high," "record," "low," "falling," and "higher."

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with extreme values, particularly high and low metrics

    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
     Orient
    -0.73
    Dialogue
    -0.69
    Ĥ¬
    -0.69
    Pict
    -0.68
    adier
    -0.66
     Sorce
    -0.65
     Regener
    -0.65
    gu
    -0.65
     Doct
    -0.64
    pres
    -0.64
    POSITIVE LOGITS
     amounts
    1.00
     liquidity
    0.92
    arcity
    0.87
     disproportion
    0.86
     concentrations
    0.84
     saturated
    0.82
     quantitative
    0.77
     (>
    0.77
     affordability
    0.77
     aggregate
    0.76
    Activations Density 0.131%

    No Known Activations