© 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. 10-RES-JB
    11. 9945
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to change and transformation, particularly in the context of technology and religion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.83
    ©¶æ
    -0.82
    aepernick
    -0.73
     DRAG
    -0.72
     Princ
    -0.71
     guiIcon
    -0.70
     Dia
    -0.68
     nas
    -0.67
    Downloadha
    -0.66
    RANT
    -0.65
    POSITIVE LOGITS
    ogue
    1.11
    og
    1.00
    angel
    0.93
    ement
    0.93
    ogs
    0.89
    mental
    0.88
    etic
    0.84
    ience
    0.84
    etics
    0.83
    ote
    0.81
    Activations Density 0.033%

    No Known Activations