INDEX

Explanations

words related to physical grasping or holding

oai_token-act-pair · gpt-3.5-turbo

references to physical grasp or control

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

actionDate

-0.78

DEF

-0.76

etheus

-0.74

ownt

-0.69

abad

-0.65

bsp

-0.64

asty

-0.62

DoS

-0.62

hemat

-0.62

ploy

-0.62

POSITIVE LOGITS

 grip

1.06

 Grip

0.97

 grips

0.95

hold

0.88

es

0.81

oire

0.81

eer

0.76

esville

0.73

 levers

0.72

raint

0.71

Activations Density 0.022%

words related to physical grasping or holding

references to physical grasp or control

No Comments

No Known Activations