INDEX

Explanations

text related to movement or traveling to a specific direction or location

oai_token-act-pair · gpt-3.5-turbo

phrases indicating direction or movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

illon

-0.74

ancies

-0.68

rehens

-0.65

orum

-0.65

eria

-0.64

DonaldTrump

-0.64

pse

-0.63

ylon

-0.61

TON

-0.61

iability

-0.61

POSITIVE LOGITS

 toward

1.13

 towards

1.09

butt

0.97

canon

0.95

liner

0.86

 downwards

0.82

lines

0.82

quarter

0.81

 into

0.79

 Ahead

0.78

Activations Density 0.045%

text related to movement or traveling to a specific direction or location

phrases indicating direction or movement

No Comments

No Known Activations