INDEX

Explanations

phrases related to actions or tasks that need to be done

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "to be" in various tenses and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

irin

-0.79

aez

-0.73

ãĤ§

-0.71

etc

-0.69

eva

-0.68

undrum

-0.66

Reading

-0.66

ilib

-0.66

Edit

-0.66

atur

-0.66

POSITIVE LOGITS

 accompanied

1.20

 preceded

1.11

 directed

1.04

 centered

1.00

 confined

0.99

 involving

0.94

 cosmetic

0.91

 tailored

0.91

 verbal

0.89

 reciprocal

0.89

Activations Density 0.313%

phrases related to actions or tasks that need to be done

occurrences of the verb "to be" in various tenses and forms

No Comments

No Known Activations