© 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. 11-RES-JB
    11. 22490
    Prev
    Next
    INDEX
    Explanations

    phrases related to the purpose or goal of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estyles
    -0.68
    KI
    -0.67
    .''.
    -0.66
    he
    -0.64
     ILCS
    -0.63
    Cause
    -0.59
    dit
    -0.59
    UV
    -0.58
    usters
    -0.57
    rine
    -0.57
    POSITIVE LOGITS
     this
    1.08
     these
    0.89
     nutshell
    0.75
     adopting
    0.71
     THIS
    0.70
     constructing
    0.69
     determining
    0.68
    this
    0.68
     distinguishing
    0.68
     most
    0.67
    Activations Density 0.283%

    No Known Activations