© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    text related to technology and computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    references to analyzing or breaking down information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aval
    -0.72
     agony
    -0.66
     unheard
    -0.65
     outraged
    -0.64
     hers
    -0.64
     Yar
    -0.64
     ecstatic
    -0.63
     offended
    -0.62
     proud
    -0.62
     amused
    -0.61
    POSITIVE LOGITS
    Overview
    1.34
    Firstly
    1.34
    Introduction
    1.23
    First
    1.20
    Definition
    1.12
    Consider
    1.09
    Appearance
    1.08
    Before
    1.06
    Reason
    1.05
     Firstly
    1.05
    Activations Density 0.454%

    No Known Activations