© 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. 7-RES-JB
    11. 2839
    Prev
    Next
    INDEX
    Explanations

    mentions related to job industries and workplaces

    oai_token-act-pair · gpt-3.5-turbo

    themes related to personal experiences and emotions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.70
    xit
    -0.64
    ¶
    -0.64
     Transcript
    -0.62
     Removal
    -0.62
     Petition
    -0.60
     Provision
    -0.59
    \":
    -0.59
     Patients
    -0.58
     Volunteers
    -0.57
    POSITIVE LOGITS
     goddamn
    1.16
     fuckin
    1.05
     damn
    1.05
     fucking
    1.03
     godd
    1.01
     shitty
    0.93
     dudes
    0.91
     shit
    0.91
     freaking
    0.89
     kinda
    0.88
    Activations Density 1.661%

    No Known Activations