INDEX

Explanations

mentions of sources or references in documents

oai_token-act-pair · gpt-3.5-turbo

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Beir

-0.71

olas

-0.69

 millenn

-0.61

Topics

-0.60

meyer

-0.59

 Petty

-0.58

igne

-0.57

paces

-0.56

iter

-0.56

AFB

-0.56

POSITIVE LOGITS

::::::::

0.90

::::

0.88

,,,,,,,,

0.88

,,,,

0.83

Pa

0.82

soon

0.80

tel

0.79

then

0.78

ãĥŁ

0.76

taboola

0.70

Activations Density 0.042%

mentions of sources or references in documents

No Comments

No Known Activations