© 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. 8688
    Prev
    Next
    INDEX
    Explanations

    instances where the word "actually" is used

    oai_token-act-pair · gpt-3.5-turbo

    the word "actually" and its repetitions to indicate emphasis or confirmation

    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
    stakes
    -0.72
     Crus
    -0.66
    VC
    -0.65
     Crusader
    -0.65
     Directive
    -0.64
    cit
    -0.63
    lain
    -0.63
     newsletters
    -0.62
     canopy
    -0.62
     Rouge
    -0.61
    POSITIVE LOGITS
     manage
    0.76
    ional
    0.74
     managed
    0.72
     existed
    0.72
    netflix
    0.70
     bother
    0.68
    ITY
    0.67
     possess
    0.67
     bothered
    0.67
     functioning
    0.66
    Activations Density 0.035%

    No Known Activations