INDEX

Explanations

references to a large or significant quantity

oai_token-act-pair · gpt-3.5-turbo

terms related to proportions and fractions within 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

 nearest

-0.73

Rim

-0.65

rones

-0.63

 Stars

-0.62

aleb

-0.62

Rav

-0.62

 ribs

-0.61

 pastor

-0.60

ucky

-0.59

imir

-0.58

POSITIVE LOGITS

(>

1.05

UID

0.77

(~

0.76

entials

0.64

YP

0.63

=\"

0.63

of

0.63

ANCE

0.63

ortment

0.63

RW

0.63

Activations Density 0.083%

references to a large or significant quantity

terms related to proportions and fractions within various contexts

No Comments

No Known Activations