© 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. 23083
    Prev
    Next
    INDEX
    Explanations

    words related to acquiring or achieving something, often in the context of improvement or advantage

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to economic benefits or advantages

    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
     Gears
    -0.66
     reckoned
    -0.66
    Synopsis
    -0.63
     densely
    -0.62
     contemplated
    -0.59
     molecule
    -0.59
     Worldwide
    -0.59
    pled
    -0.57
    ``
    -0.55
     testifying
    -0.55
    POSITIVE LOGITS
    esville
    1.10
    aroo
    0.92
    eful
    0.85
    llor
    0.84
    /+
    0.82
    icult
    0.80
     gain
    0.80
    nir
    0.80
    iage
    0.77
    esses
    0.77
    Activations Density 0.016%

    No Known Activations