© 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. 8015
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles or barriers

    oai_token-act-pair · gpt-3.5-turbo

    words related to obstacles and barriers to progress or success

    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
    zsche
    -0.68
    orf
    -0.67
    iren
    -0.64
    inav
    -0.64
    ivery
    -0.64
    esome
    -0.63
    essage
    -0.63
    tan
    -0.63
    ergy
    -0.62
    atorium
    -0.62
    POSITIVE LOGITS
     barriers
    1.02
     erected
    1.00
     obstacle
    1.00
     obstacles
    0.98
     preventing
    0.96
     overcome
    0.87
     impede
    0.86
     separating
    0.85
     imped
    0.85
     barrier
    0.84
    Activations Density 0.044%

    No Known Activations