INDEX

Explanations

phrases starting with the word 'Many of'

oai_token-act-pair · gpt-3.5-turbo

the frequent repetition of the phrase "of" 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

dayName

-0.80

ĸļ

-0.79

acus

-0.78

berus

-0.76

bet

-0.75

uyomi

-0.71

 cape

-0.68

abba

-0.68

 allot

-0.66

ocracy

-0.66

POSITIVE LOGITS

 course

0.75

course

0.70

 applicants

0.66

 Lies

0.64

 meantime

0.64

 COUR

0.64

us

0.58

ortunately

0.58

 respondents

0.56

 Kent

0.55

Activations Density 0.116%

phrases starting with the word 'Many of'

the frequent repetition of the phrase "of" in various contexts

No Comments

No Known Activations