© 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. 18528
    Prev
    Next
    INDEX
    Explanations

    information related to individuals who work on or are associated with various projects and products

    oai_token-act-pair · gpt-3.5-turbo

    references to directors and their notable works

    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
    Newsletter
    -0.86
     deterrent
    -0.80
     deterrence
    -0.69
    oral
    -0.69
    WASHINGTON
    -0.68
     voters
    -0.68
    Vote
    -0.67
    otte
    -0.67
     avoidance
    -0.66
    constitutional
    -0.65
    POSITIVE LOGITS
     renown
    1.16
     famed
    1.10
     infamous
    1.07
     famously
    1.06
     aforementioned
    0.99
     renowned
    0.98
     legendary
    0.98
     collaborations
    0.97
     notorious
    0.95
     notoriously
    0.94
    Activations Density 0.734%

    No Known Activations