© 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. 10813
    Prev
    Next
    INDEX
    Explanations

    two conflicting aspects or entities

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "but also" indicating contrast or addition

    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
    jam
    -0.79
    crow
    -0.72
    Ash
    -0.65
    Ur
    -0.64
    enter
    -0.64
    Wr
    -0.63
    ichen
    -0.63
    Focus
    -0.63
    ysis
    -0.63
    atre
    -0.63
    POSITIVE LOGITS
     includes
    0.88
     occasionally
    0.84
     optionally
    0.83
     incorporates
    0.82
     cautioned
    0.80
     included
    0.77
     hinted
    0.76
     prov
    0.76
     ensured
    0.75
     risked
    0.74
    Activations Density 0.078%

    No Known Activations