INDEX

Explanations

words related to beans

oai_token-act-pair · gpt-3.5-turbo

mentions of "bean" and "beans."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ngth

-0.84

Ö¼

-0.76

cffff

-0.74

utherford

-0.74

untled

-0.73

umbn

-0.72

hematic

-0.71

pload

-0.71

uyomi

-0.70

angelo

-0.68

POSITIVE LOGITS

bean

1.15

beans

1.00

bag

1.00

bags

0.98

ie

0.91

 Beans

0.88

aign

0.87

 Bean

0.85

 beans

0.85

stocks

0.84

Activations Density 0.017%

words related to beans

mentions of "bean" and "beans."

No Comments

No Known Activations