© 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. 2-RES-JB
    11. 727
    Prev
    Next
    INDEX
    Explanations

    compound words containing the suffix '-brush', '-grass', '-pants', '-roots', and '-forest'

    oai_token-act-pair · gpt-4-turbo

    clothing items

    oai_token-act-pair · gpt-3.5-turbo

    objects and concepts related to nature and personal items

    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
    NL
    -0.74
    asio
    -0.63
     WCS
    -0.62
     MIL
    -0.61
    ENN
    -0.60
     colon
    -0.60
     Trib
    -0.59
    OTOS
    -0.59
     aggress
    -0.58
     CLS
    -0.56
    POSITIVE LOGITS
    theless
    1.13
    ertodd
    0.97
    DragonMagazine
    0.94
    tenance
    0.84
    tics
    0.83
    ionage
    0.82
    Mania
    0.80
    hyde
    0.77
    giving
    0.77
    racuse
    0.76
    Activations Density 0.178%

    No Known Activations