© 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. 9-RES-JB
    11. 5073
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and expression

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to societal observations and critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    License
    -0.66
    Merit
    -0.62
    Assembly
    -0.61
    urable
    -0.61
     overcame
    -0.61
    Had
    -0.59
    disabled
    -0.59
     Vish
    -0.58
    izable
    -0.58
     Federation
    -0.58
    POSITIVE LOGITS
     invariably
    1.53
     usually
    1.43
     typically
    1.23
     inevitably
    1.22
    usually
    1.13
     automatically
    1.11
     often
    1.10
     tend
    1.08
     tends
    1.07
     ALWAYS
    1.06
    Activations Density 0.483%

    No Known Activations