© 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. 8-RES-JB
    11. 20159
    Prev
    Next
    INDEX
    Explanations

    places or entities with the term "inn" in their name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "inn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rero
    -0.69
    ©¶æ
    -0.65
    ¶æ
    -0.65
    lda
    -0.64
     litter
    -0.63
     Nile
    -0.63
    ques
    -0.62
    ============
    -0.60
    rely
    -0.59
    Cooldown
    -0.59
    POSITIVE LOGITS
    ipeg
    1.76
    ovation
    1.38
    ikuman
    1.17
    spir
    1.15
    ocent
    1.09
    itus
    1.08
    igan
    1.06
    osuke
    1.04
    igans
    1.04
    umerable
    1.02
    Activations Density 0.036%

    No Known Activations