© 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. 6689
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualities or features of things

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the existence or presence of certain problems or characteristics

    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
    ²¾
    -0.90
    opian
    -0.78
    arest
    -0.76
    anches
    -0.74
    iddles
    -0.72
    eli
    -0.72
    姫
    -0.72
    isms
    -0.71
     Roads
    -0.71
    enders
    -0.71
    POSITIVE LOGITS
     kind
    1.47
     type
    1.40
     sort
    1.34
     kinds
    1.02
     capability
    1.02
     exact
    0.99
     happen
    0.98
     trope
    0.97
     tactic
    0.97
     happening
    0.96
    Activations Density 0.188%

    No Known Activations