© 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. 1-RES-JB
    11. 22501
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Barn" in various contexts and locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Barn" and its variations in different 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
    ffic
    -0.75
     regret
    -0.74
    EP
    -0.64
    ctors
    -0.64
    INTER
    -0.63
    stanbul
    -0.63
    FORMATION
    -0.62
    ICT
    -0.62
     transcription
    -0.59
    lda
    -0.59
    POSITIVE LOGITS
     Barn
    1.23
    aby
    1.19
    acle
    1.10
    acles
    1.07
    Barn
    1.04
    abal
    0.97
    ataka
    0.95
    azz
    0.92
    MpServer
    0.92
    ues
    0.91
    Activations Density 0.005%

    No Known Activations