© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    prepositions 'to' followed by target recipients or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of giving or delivering information

    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
     empt
    -0.73
     deductions
    -0.66
     substit
    -0.66
     thereto
    -0.64
     delegated
    -0.63
     (&
    -0.63
     travers
    -0.63
    ahime
    -0.62
    ices
    -0.62
    addons
    -0.62
    POSITIVE LOGITS
     coincide
    1.31
    pless
    1.16
     accompany
    1.06
     commemorate
    1.00
     reassure
    0.91
     illustrate
    0.89
     appease
    0.88
     cheers
    0.87
     reporters
    0.85
     celebrate
    0.84
    Activations Density 0.195%

    No Known Activations