© 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. 9-RES-JB
    11. 1821
    Prev
    Next
    INDEX
    Explanations

    phrases related to a wide variety of topics, including research, health care, formulations, and services

    oai_token-act-pair · gpt-3.5-turbo

    symbols and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oldown
    -0.67
    lly
    -0.64
    earing
    -0.60
     LIA
    -0.58
     cause
    -0.58
    ahime
    -0.58
    orically
    -0.56
     midway
    -0.56
    aii
    -0.56
     fool
    -0.55
    POSITIVE LOGITS
    including
    1.65
     Including
    1.27
     including
    1.24
     namely
    1.12
    mostly
    1.11
    excluding
    1.04
    particularly
    1.02
    ranging
    0.98
     includ
    0.98
    those
    0.97
    Activations Density 0.228%

    No Known Activations