INDEX

Explanations

words indicating discovery or realization

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "find" in various contexts

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

fue

-0.67

 partic

-0.66

idium

-0.65

 paced

-0.64

istry

-0.63

isoft

-0.62

 captcha

-0.62

 concess

-0.61

inion

-0.60

brance

-0.60

POSITIVE LOGITS

omething

0.79

½

0.77

ById

0.76

ãĤ¼

0.75

-+-+

0.75

ãĤ¤ãĥĪ

0.74

ibility

0.70

Ö¼

0.68

ä½¿

0.68

ource

0.67

Activations Density 0.063%

words indicating discovery or realization

occurrences of the word "find" in various contexts

No Comments

No Known Activations