© 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. 2-RES-JB
    11. 9423
    Prev
    Next
    INDEX
    Explanations

    words related to operations and cooperative terms

    oai_token-act-pair · gpt-3.5-turbo

    references to operational processes and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vengeance
    -0.67
     Primordial
    -0.63
     haste
    -0.63
     Fey
    -0.62
     afore
    -0.62
     Allaah
    -0.60
    definition
    -0.59
    xual
    -0.59
     blond
    -0.59
     wealth
    -0.59
    POSITIVE LOGITS
    oper
    1.14
    aquin
    1.00
    ament
    0.99
    atives
    0.90
    ops
    0.84
    ational
    0.83
    ating
    0.83
    aton
    0.82
    acus
    0.81
    inson
    0.79
    Activations Density 0.008%

    No Known Activations