INDEX

Explanations

words related to continuous or ongoing actions or processes

oai_token-act-pair · gpt-3.5-turbo

words that end with "ing" or "ed"

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

hee

-0.78

edom

-0.75

ushing

-0.71

tery

-0.69

agy

-0.69

apult

-0.66

agna

-0.66

analysis

-0.63

heast

-0.63

 Byrd

-0.63

POSITIVE LOGITS

rils

0.72

lich

0.70

ends

0.68

ending

0.68

uality

0.68

ulum

0.65

ENDED

0.65

ught

0.64

lessly

0.64

ended

0.63

Activations Density 0.021%

words related to continuous or ongoing actions or processes

words that end with "ing" or "ed"

No Comments

No Known Activations