© 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. 7-RES-JB
    11. 4600
    Prev
    Next
    INDEX
    Explanations

    phrases starting with conjunctions such as 'so', 'and', 'but', and 'or'

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and connecting words that indicate speaker orientation and personal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lyme
    -0.61
     NES
    -0.58
     )))
    -0.58
     Ranch
    -0.57
     Duc
    -0.56
     Reef
    -0.55
     Vita
    -0.54
     crop
    -0.54
     Bat
    -0.54
     unsus
    -0.53
    POSITIVE LOGITS
    ulty
    1.00
    theless
    0.95
    etheless
    0.92
    zbollah
    0.91
    selves
    0.91
    ngth
    0.91
    icularly
    0.89
    initely
    0.87
    mosp
    0.87
    etheus
    0.87
    Activations Density 0.219%

    No Known Activations