INDEX

Explanations

contractions and negations

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing conditional situations or statements

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

NetMessage

-0.68

nesota

-0.63

onement

-0.63

.............

-0.63

 Royale

-0.63

etts

-0.61

 Excellence

-0.59

 Selection

-0.59

 Mobility

-0.58

 Shame

-0.57

POSITIVE LOGITS

 technically

0.94

 disagree

0.81

 disagreed

0.79

 trivial

0.78

 momentarily

0.77

 admittedly

0.73

 physically

0.73

 slight

0.73

 otherwise

0.71

 consciously

0.71

Activations Density 0.175%

contractions and negations

phrases emphasizing conditional situations or statements

No Comments

No Known Activations