© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17756
    Prev
    Next
    INDEX
    Explanations

    words related to hindering, obstructing, or preventing something

    oai_token-act-pair · gpt-3.5-turbo

    references to obstruction or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olate
    -0.74
    rum
    -0.70
    elt
    -0.68
    lli
    -0.68
    emic
    -0.67
    rious
    -0.65
    rics
    -0.65
    orically
    -0.64
    nai
    -0.64
     Volunte
    -0.64
    POSITIVE LOGITS
     access
    1.04
     entrance
    0.82
     accessing
    0.81
    ades
    0.78
     entrances
    0.78
    buster
    0.76
     doorway
    0.76
    aded
    0.75
     entry
    0.74
     progress
    0.72
    Activations Density 0.093%

    No Known Activations