© 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. 7-RES-JB
    11. 21373
    Prev
    Next
    INDEX
    Explanations

    terms indicating measurement and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    terms that refer to indicators or predictors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
    uthor
    -0.78
    \\\\\\\\
    -0.73
    ©¶æ
    -0.72
    ulhu
    -0.71
    porting
    -0.71
    sis
    -0.70
    CLASSIFIED
    -0.70
     Kirin
    -0.70
    TPP
    -0.69
    POSITIVE LOGITS
     indicators
    1.00
     markers
    0.97
     predictive
    0.90
     measuring
    0.88
     variables
    0.85
     assessing
    0.85
     marker
    0.84
     measure
    0.82
     gauge
    0.82
     correlated
    0.81
    Activations Density 0.148%

    No Known Activations