INDEX

Explanations

words related to suggestions or recommendations

oai_token-act-pair · gpt-3.5-turbo

references to suggestions and recommendations

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

ipel

-0.84

ophon

-0.79

ewitness

-0.70

yrs

-0.68

estine

-0.68

zona

-0.66

rooms

-0.66

tiny

-0.66

cop

-0.66

mberg

-0.66

POSITIVE LOGITS

 sugg

0.91

uyomi

0.83

 suggestions

0.80

uggest

0.77

ļéĨĴ

0.75

 suggestion

0.73

 guideline

0.72

 recommendation

0.72

 è£ıç

0.70

 overload

0.70

Activations Density 0.032%

words related to suggestions or recommendations

references to suggestions and recommendations

No Comments

No Known Activations