INDEX

Explanations

the word "Dav" followed by either a single digit or the digits "os" and sometimes followed by additional characters

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Davao."

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

ACTED

-0.70

©¶æ

-0.64

PDATE

-0.64

 occup

-0.64

 electric

-0.62

 Fired

-0.62

 caption

-0.61

TRY

-0.60

WAYS

-0.59

CLASS

-0.59

POSITIVE LOGITS

inas

0.98

isco

0.98

ildo

0.97

iral

0.96

illon

0.93

inelli

0.93

ict

0.91

isson

0.90

olla

0.88

oker

0.88

Activations Density 0.012%

the word "Dav" followed by either a single digit or the digits "os" and sometimes followed by additional characters

occurrences of the name "Davao."

No Comments

No Known Activations