© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    instances where a photo or image is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference photographs and their context, particularly the act of taking them

    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
     punish
    -0.80
     regress
    -0.75
    egg
    -0.71
    estinal
    -0.71
    lear
    -0.70
    lishes
    -0.70
    regulated
    -0.69
     subsid
    -0.68
    emonic
    -0.67
     clause
    -0.66
    POSITIVE LOGITS
     photographs
    0.96
     Photographer
    0.95
     photographers
    0.93
     Nikon
    0.93
     photographed
    0.93
     Mehran
    0.92
     photograp
    0.91
     filmed
    0.91
     snapshots
    0.88
     footage
    0.88
    Activations Density 0.090%

    No Known Activations