© 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. 1-RES-JB
    11. 24055
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "blocking" or "obstructing"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "block" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bil
    -0.66
    mob
    -0.66
     orally
    -0.65
    eworks
    -0.63
    Win
    -0.63
    mes
    -0.62
     Plat
    -0.61
    bet
    -0.61
     civ
    -0.61
     shatter
    -0.61
    POSITIVE LOGITS
    ocking
    1.08
    OCK
    0.85
    ocks
    0.84
    jay
    0.84
    ocked
    0.80
    bird
    0.79
    oaded
    0.76
    odon
    0.74
    abilia
    0.74
    ONDON
    0.71
    Activations Density 0.005%

    No Known Activations