INDEX

Explanations

phrases related to direction or movement

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 @ 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

iability

-0.72

 Corpus

-0.66

sylvania

-0.62

Mub

-0.62

TON

-0.62

rehens

-0.61

illon

-0.60

asions

-0.60

bos

-0.60

orum

-0.60

POSITIVE LOGITS

canon

1.09

liner

0.90

heading

0.88

lines

0.86

line

0.85

pin

0.85

pins

0.85

quarter

0.83

lander

0.82

 toward

0.81

Activations Density 0.021%

phrases related to direction or movement

phrases indicating direction or movement

No Comments

No Known Activations