© 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. 9452
    Prev
    Next
    INDEX
    Explanations

    mentions of aid and assistance

    oai_token-act-pair · gpt-3.5-turbo

    references to humanitarian aid

    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
     Bellev
    -0.76
     Beard
    -0.70
    é¾
    -0.70
     Ran
    -0.68
     Coat
    -0.63
     Grind
    -0.63
     Beau
    -0.62
     aber
    -0.60
     Mamm
    -0.59
    chrom
    -0.57
    POSITIVE LOGITS
     aid
    1.16
    glers
    0.88
     Aid
    0.86
    maid
    0.81
    giving
    0.80
    aments
    0.78
     aids
    0.78
    lift
    0.77
    ilitation
    0.76
    uese
    0.76
    Activations Density 0.010%

    No Known Activations