© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming like 'DL', 'OL', and 'RB'

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations related to data labels or positions in a dataset

    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
    flies
    -0.79
    ãĤ¡
    -0.76
    ãĥ¼ãĥĨ
    -0.72
     Samoa
    -0.70
    lies
    -0.69
    ãĥ£
    -0.68
    achu
    -0.66
    ãĤ±
    -0.66
     Huff
    -0.66
    ulatory
    -0.65
    POSITIVE LOGITS
    owship
    1.01
    anguage
    0.95
    uce
    0.94
    DL
    0.94
    ibrary
    0.93
    ensor
    0.90
    ouble
    0.89
     DL
    0.89
    inking
    0.85
    iamond
    0.84
    Activations Density 0.009%

    No Known Activations