© 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. 11656
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and potential action

    oai_token-act-pair · gpt-3.5-turbo

    instructions or actions directed towards the reader

    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
     memorandum
    -0.68
     silence
    -0.63
     footsteps
    -0.63
     Guest
    -0.60
     fragmentation
    -0.59
     Notting
    -0.59
     MR
    -0.58
     Rooms
    -0.58
     futile
    -0.58
     ACPI
    -0.57
    POSITIVE LOGITS
    »Ĵ
    0.96
    968
    0.80
    ¶ħ
    0.80
    ģĸ
    0.73
    Used
    0.69
    \\\\\\\\
    0.68
    OTO
    0.68
    inate
    0.66
     teasp
    0.64
    claimed
    0.64
    Activations Density 0.416%

    No Known Activations