INDEX

Explanations

mentions of specific words, likely related to a particular topic or entity named "Stone"

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

phis

-0.73

olulu

-0.72

NCT

-0.69

orescence

-0.68

oresc

-0.65

merce

-0.65

unal

-0.65

ornia

-0.64

ITAL

-0.63

Demand

-0.63

POSITIVE LOGITS

lings

0.95

hill

0.92

ring

0.87

works

0.86

falls

0.85

zman

0.81

bilt

0.81

 Cold

0.80

hook

0.80

 Roses

0.80

Activations Density 0.024%

mentions of specific words, likely related to a particular topic or entity named "Stone"

No Comments

No Known Activations