© 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. 4-RES-JB
    11. 14927
    Prev
    Next
    INDEX
    Explanations

    mentions of different versions of Google Nexus phones

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Nexus" concept in various contexts

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

    No Comments

    Negative Logits
    ischer
    -1.05
    lasses
    -0.89
    arning
    -0.85
    orget
    -0.83
    loss
    -0.83
    lass
    -0.81
    ulton
    -0.79
    ffen
    -0.78
    inse
    -0.76
    akespe
    -0.76
    POSITIVE LOGITS
     Nexus
    1.02
    mods
    0.88
     Mods
    0.86
    peria
    0.81
    Mods
    0.79
    Pad
    0.75
     Device
    0.75
    Guide
    0.73
    umeric
    0.73
     Protector
    0.73
    Activations Density 0.011%

    No Known Activations