© 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. 0-RES-JB
    11. 11561
    Prev
    Next
    INDEX
    Explanations

    words related to communication barriers or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    references to phone calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subject
    -0.74
     Category
    -0.64
     jud
    -0.64
     Bard
    -0.61
     methodology
    -0.59
     success
    -0.59
     Title
    -0.59
     preparation
    -0.59
     age
    -0.59
     plaus
    -0.58
    POSITIVE LOGITS
    alls
    4.66
    alled
    2.34
    alling
    2.25
    ALL
    1.93
    all
    1.92
    ells
    1.32
    als
    1.26
    arms
    1.15
    ills
    1.15
    reens
    1.14
    Activations Density 0.010%

    No Known Activations