INDEX

Explanations

phrases or terms related to seeking or obtaining approval

oai_token-act-pair · gpt-3.5-turbo

references to approval 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

hed

-0.84

gm

-0.81

lla

-0.76

hester

-0.74

hematic

-0.66

ãĤ©

-0.65

âĵĺ

-0.64

apon

-0.64

grave

-0.64

 Canaver

-0.63

POSITIVE LOGITS

 ratings

1.03

 approval

1.02

 approvals

1.02

 rating

0.98

worthy

0.88

 commissions

0.87

 approves

0.82

rador

0.81

 authorizing

0.81

 clearance

0.81

Activations Density 0.028%

phrases or terms related to seeking or obtaining approval

references to approval in various contexts

No Comments

No Known Activations