INDEX

Explanations

phrases expressing disbelief or strong negative emotions

oai_token-act-pair · gpt-3.5-turbo

expressions of disbelief or incredulity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aukee

-0.82

 exting

-0.76

iHUD

-0.74

incial

-0.72

orage

-0.70

abase

-0.67

tails

-0.66

kamp

-0.66

ãĥīãĥ©

-0.66

´

-0.65

POSITIVE LOGITS

 someone

1.17

 somebody

1.06

 anyone

0.96

 nobody

0.90

someone

0.85

 anybody

0.83

 they

0.81

we

0.79

 people

0.77

 somehow

0.76

Activations Density 0.115%

phrases expressing disbelief or strong negative emotions

expressions of disbelief or incredulity

No Comments

No Known Activations