© 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. 8996
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or tasks that a person can physically perform

    oai_token-act-pair · gpt-3.5-turbo

    infinitive phrases that indicate actions or intentions

    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
     tariffs
    -0.65
     probabilities
    -0.62
    Downloadha
    -0.60
     exceptions
    -0.60
    Got
    -0.60
     Investor
    -0.58
     conced
    -0.58
    ieth
    -0.58
     declines
    -0.57
    except
    -0.56
    POSITIVE LOGITS
     accompany
    1.27
     commemorate
    1.16
     replace
    1.14
     satisfy
    1.13
     emulate
    1.11
     distribute
    1.09
     illustrate
    1.03
     counteract
    1.02
     enhance
    1.00
     celebrate
    1.00
    Activations Density 0.217%

    No Known Activations