© 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. 20280
    Prev
    Next
    INDEX
    Explanations

    actions related to proposing, enacting, or changing laws and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making or enacting changes or policies

    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
    rina
    -0.72
    anwhile
    -0.72
     scrimmage
    -0.70
    cum
    -0.69
     Examiner
    -0.68
    CLOSE
    -0.64
    assis
    -0.64
    sonian
    -0.64
    inen
    -0.63
    etts
    -0.63
    POSITIVE LOGITS
     sure
    1.24
     strides
    0.86
     allowances
    0.84
     available
    0.83
    roads
    0.82
     distinctions
    0.81
     clear
    0.78
     accommodations
    0.78
     improvements
    0.78
     Sure
    0.77
    Activations Density 0.112%

    No Known Activations