INDEX

Explanations

phrases related to action or movement

oai_token-act-pair · gpt-3.5-turbo

phrases related to initiating actions or events

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

otten

-0.81

ever

-0.73

ums

-0.72

zzy

-0.72

asca

-0.69

ube

-0.69

uddy

-0.69

anche

-0.69

panel

-0.69

gor

-0.68

POSITIVE LOGITS

 havoc

0.75

EMENT

0.65

 ILCS

0.61

FI

0.60

 defences

0.60

 linem

0.59

 attRot

0.59

 whereby

0.59

HER

0.58

 detachment

0.58

Activations Density 0.062%

phrases related to action or movement

phrases related to initiating actions or events

No Comments

No Known Activations