© 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. 1-RES-JB
    11. 9495
    Prev
    Next
    INDEX
    Explanations

    words related to operations or procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to operational procedures or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afore
    -0.60
    llah
    -0.59
    ¿½
    -0.59
    eree
    -0.58
     nod
    -0.58
     haste
    -0.57
     fateful
    -0.57
     Primordial
    -0.57
     vengeance
    -0.56
     blonde
    -0.56
    POSITIVE LOGITS
    oper
    1.25
    aquin
    0.97
    ament
    0.96
    operation
    0.88
    ops
    0.85
    TAIN
    0.81
    asis
    0.81
    phabet
    0.79
    VPN
    0.79
    OPER
    0.78
    Activations Density 0.007%

    No Known Activations