© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    phrases discussing opinions or beliefs about moral or ethical issues

    oai_token-act-pair · gpt-3.5-turbo
    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
    isode
    -0.75
    76561
    -0.73
    ãĤ©
    -0.71
    ertodd
    -0.65
    details
    -0.65
    cific
    -0.64
    ffe
    -0.64
    nergy
    -0.62
     trailed
    -0.62
    ttp
    -0.60
    POSITIVE LOGITS
     imperative
    1.31
     permissible
    1.27
     advisable
    1.23
     possible
    1.22
     impossible
    1.20
     conceivable
    1.16
     incumbent
    1.11
     feasible
    1.11
     desirable
    1.11
     prudent
    1.10
    Activations Density 0.212%

    No Known Activations