© 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. 17059
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly "Blanc" and "Malkin"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    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
    #$
    -0.74
    WARE
    -0.70
    ngth
    -0.70
     ILCS
    -0.70
     Defenders
    -0.70
     Slot
    -0.68
    FFER
    -0.65
    CLAIM
    -0.64
    ©¶æ¥µ
    -0.62
    ictionary
    -0.62
    POSITIVE LOGITS
    sis
    0.85
    enary
    0.82
    inx
    0.81
     Blanc
    0.77
    eas
    0.75
    gio
    0.75
    inos
    0.73
    ère
    0.72
    uci
    0.71
    het
    0.70
    Activations Density 0.011%

    No Known Activations