INDEX

Explanations

references to the number 7

oai_token-act-pair · gpt-3.5-turbo

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ument

-0.81

gart

-0.73

ennes

-0.68

ploy

-0.61

plom

-0.60

 bearer

-0.59

rique

-0.59

 relat

-0.59

ocard

-0.58

 tract

-0.58

POSITIVE LOGITS

 Wonders

1.09

ecause

0.97

ioned

0.93

eenth

0.92

0.90

th

0.88

0.85

0.84

0.83

een

0.83

Activations Density 0.087%

references to the number 7

No Comments

No Known Activations