© 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. 3256
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "FIR" standing for "First Information Report" in the context of legal or investigative documents

    oai_token-act-pair · gpt-3.5-turbo

    descriptions and mentions of FIR (First Information Reports) 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
    itals
    -0.68
    iste
    -0.66
     hotel
    -0.64
    ocratic
    -0.63
     Jefferson
    -0.61
     Huck
    -0.61
     Observer
    -0.60
     Sinclair
    -0.59
    Machine
    -0.59
     Mellon
    -0.58
    POSITIVE LOGITS
     FIR
    1.40
    terness
    1.02
    igree
    0.87
    teenth
    0.86
    FIR
    0.83
     corrid
    0.78
    ²¾
    0.76
    FI
    0.76
    eworks
    0.75
    shaw
    0.75
    Activations Density 0.014%

    No Known Activations