© 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. 3-RES-JB
    11. 14719
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms with 'PC' as part of their term

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.98
    ãĥĥ
    -0.74
    ãĥĦ
    -0.74
    ãĤ¤ãĥĪ
    -0.69
    ymes
    -0.67
     Bie
    -0.65
    fulness
    -0.65
    quez
    -0.64
    ãĥį
    -0.63
    bang
    -0.63
    POSITIVE LOGITS
    PC
    1.02
    rint
    0.90
    ACE
    0.81
    GS
    0.80
    ategory
    0.79
    ridges
    0.79
    onduct
    0.78
    ORPG
    0.78
    ombat
    0.77
    ustom
    0.76
    Activations Density 0.009%

    No Known Activations