© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams or competitions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring 'ourn' within words

    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
    plates
    -0.72
    RECT
    -0.63
    Effective
    -0.61
    FU
    -0.61
     twin
    -0.60
    DIV
    -0.60
    BALL
    -0.59
     multiplication
    -0.58
     Rossi
    -0.56
    TRUMP
    -0.55
    POSITIVE LOGITS
    emouth
    1.57
    oir
    1.20
    ette
    1.08
    ourn
    1.07
    nette
    1.00
    ique
    0.96
    ettes
    0.96
    ville
    0.93
    oyer
    0.91
    ues
    0.90
    Activations Density 0.040%

    No Known Activations