INDEX

Explanations

phrases involving punishment or criticism

oai_token-act-pair · gpt-3.5-turbo

references to the concept of punishment or reprimand

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quickShipAvailable

-0.81

natureconservancy

-0.77

ItemImage

-0.72

 Belief

-0.71

 Hemp

-0.71

VIEW

-0.70

ENTS

-0.68

tis

-0.67

éĸ

-0.67

 Emin

-0.67

POSITIVE LOGITS

 slap

1.10

stick

1.05

dash

1.04

 slapped

1.00

dab

0.92

creen

0.86

 elbows

0.85

bowl

0.84

 slapping

0.84

gery

0.84

Activations Density 0.026%

phrases involving punishment or criticism

references to the concept of punishment or reprimand

No Comments

No Known Activations