© 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. 2-RES-JB
    11. 17747
    Prev
    Next
    INDEX
    Explanations

    occurrences related to the concept of "low"

    oai_token-act-pair · gpt-3.5-turbo

    references to low quality or low value attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.80
    thus
    -0.78
    andise
    -0.78
     Mahjong
    -0.76
    arium
    -0.74
    âĹ¼
    -0.73
     Orient
    -0.72
     Forbidden
    -0.71
    Advertisements
    -0.69
    ophers
    -0.69
    POSITIVE LOGITS
     enough
    0.94
     dipping
    0.84
     pitched
    0.83
    est
    0.79
     hanging
    0.77
    ened
    0.73
     priced
    0.73
     paced
    0.73
     doses
    0.73
     low
    0.71
    Activations Density 0.023%

    No Known Activations