INDEX

Explanations

action verbs related to changing, fixing, or transforming things

oai_token-act-pair · gpt-3.5-turbo

verbs associated with actions or processes of change and improvement

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

dt

-0.60

si

-0.60

see

-0.59

so

-0.58

behind

-0.58

debian

-0.56

tar

-0.56

talk

-0.55

eria

-0.55

Ã¨re

-0.54

POSITIVE LOGITS

redients

0.89

 oneself

0.80

BuyableInstoreAndOnline

0.71

ADRA

0.64

HAM

0.59

 INTO

0.58

issance

0.57

ãĥ¼ãĥĨ

0.55

 constituents

0.55

olphin

0.55

Activations Density 0.491%

action verbs related to changing, fixing, or transforming things

verbs associated with actions or processes of change and improvement

No Comments

No Known Activations