INDEX

Explanations

references to the term "Info"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "info" 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

 notor

-0.79

lock

-0.74

Interstitial

-0.69

ricular

-0.66

negie

-0.65

 recess

-0.63

kus

-0.63

mand

-0.63

atos

-0.62

yrus

-0.62

POSITIVE LOGITS

kson

0.84

ãĤ¿

0.83

imei

0.80

 glean

0.79

 info

0.74

cloth

0.74

ession

0.71

imation

0.71

pec

0.70

information

0.70

Activations Density 0.014%

references to the term "Info"

mentions of the word "info" in various contexts

No Comments

No Known Activations