© 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. 948
    Prev
    Next
    INDEX
    Explanations

    text related to coding and programming, specifically focusing on arrays and variables

    oai_token-act-pair · gpt-3.5-turbo

    specific programming or formatting syntax related to code or data structures

    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
    HCR
    -0.85
    resent
    -0.78
    ivation
    -0.75
    ivated
    -0.75
    IFF
    -0.74
    ivating
    -0.74
    IAN
    -0.72
    ogle
    -0.71
    FA
    -0.71
    ILY
    -0.71
    POSITIVE LOGITS
    abase
    0.80
     Clown
    0.68
    enary
    0.65
    uria
    0.64
     Dim
    0.64
     Centauri
    0.62
     shores
    0.60
     Mull
    0.59
     Mile
    0.58
     Collins
    0.58
    Activations Density 0.000%

    No Known Activations