© 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. 2-RES-JB
    6. 9501
    Prev
    Next
    INDEX
    Explanations

    mentions of the acronym "IG" followed by a number which seems to indicate the importance or relevance of the mention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "IG" related to organizational or governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.74
     Nurs
    -0.67
     Shore
    -0.66
     Dresden
    -0.65
     Gingrich
    -0.65
     Franch
    -0.64
     Belg
    -0.64
    pron
    -0.64
     Bellev
    -0.64
     Ambrose
    -0.62
    POSITIVE LOGITS
    IG
    1.13
    GER
    1.12
    INAL
    1.09
    HER
    1.01
    NING
    0.95
    TE
    0.94
    rig
    0.93
    SU
    0.91
    ITAL
    0.91
    RA
    0.90
    Activations Density 0.005%

    No Known Activations