© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons, motives, or causes

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements about reasons, importance, and the nature of situations

    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
     sqor
    -0.66
    jri
    -0.66
    abase
    -0.64
    iewicz
    -0.63
     dismant
    -0.61
     fulfil
    -0.61
     premises
    -0.60
     feasibility
    -0.59
     simulac
    -0.58
     Ala
    -0.58
    POSITIVE LOGITS
    Reviewer
    0.92
    forth
    0.85
     bothering
    0.84
    ãĤ»
    0.83
     so
    0.79
     bother
    0.79
     reluctant
    0.77
     singled
    0.77
     persist
    0.77
     hesitant
    0.75
    Activations Density 0.169%

    No Known Activations