© 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. 819
    Prev
    Next
    INDEX
    Explanations

    words starting with 'Sop' and 'glob'

    oai_token-act-pair · gpt-4-turbo

    names of organizations, politicians, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters, entities, or categories, particularly in political or scientific contexts

    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
    fact
    -0.72
    ________________________
    -0.71
     Blackwell
    -0.70
    que
    -0.67
    osaurs
    -0.66
    doors
    -0.65
    ieving
    -0.64
    ¿½
    -0.64
    Wheel
    -0.63
    ranged
    -0.62
    POSITIVE LOGITS
     Cosponsors
    0.96
    ulla
    0.94
    éĹĺ
    0.89
    etooth
    0.89
    mble
    0.85
    iets
    0.84
    lication
    0.84
    lio
    0.81
    ersen
    0.80
    elist
    0.79
    Activations Density 0.019%

    No Known Activations