© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    commanding phrases suggesting action or engagement

    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
    bara
    -0.81
    quartered
    -0.75
    éĹ
    -0.70
    lied
    -0.69
    otten
    -0.65
    ELD
    -0.64
    KO
    -0.63
    ago
    -0.63
    alky
    -0.62
    pine
    -0.60
    POSITIVE LOGITS
     ourselves
    1.07
     together
    0.71
     OUR
    0.68
    querade
    0.66
     clarify
    0.64
     anew
    0.64
     aside
    0.63
     collectively
    0.63
     REAL
    0.62
     tomorrow
    0.62
    Activations Density 0.102%

    No Known Activations