© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6114
    Prev
    Next
    INDEX
    Explanations

    phrases related to hindering or obstructing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "block" and its variations in legal and regulatory contexts

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

    No Comments

    Negative Logits
    lycer
    -0.82
     Understanding
    -0.74
    lli
    -0.73
    Truth
    -0.67
    rics
    -0.66
    alt
    -0.65
    aghd
    -0.63
     Understand
    -0.63
    vity
    -0.62
     Suc
    -0.61
    POSITIVE LOGITS
     blocking
    0.86
    aded
    0.79
    picking
    0.74
     filib
    0.74
    buster
    0.73
     stacking
    0.72
     opposing
    0.71
    busters
    0.71
     obstruct
    0.69
     obstruction
    0.69
    Activations Density 0.026%

    No Known Activations