INDEX

Explanations

technical terms related to processes or actions

oai_token-act-pair · gpt-3.5-turbo

terms related to actions, processes, and administrative aspects

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Typh

-0.64

 Roses

-0.63

senal

-0.63

Ever

-0.59

 murdering

-0.58

Ta

-0.57

NEWS

-0.56

 Aires

-0.56

Tax

-0.56

Blood

-0.56

POSITIVE LOGITS

 requirement

0.90

 mechanism

0.88

 consisted

0.87

 ensures

0.86

 consists

0.85

 lasts

0.84

 signifies

0.84

 entails

0.83

 includes

0.81

 expires

0.81

Activations Density 0.471%

technical terms related to processes or actions

terms related to actions, processes, and administrative aspects

No Comments

No Known Activations