INDEX

Explanations

phrases related to instructions or tips

oai_token-act-pair · gpt-3.5-turbo

markers indicating the beginning or end of segments in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 escaping

-0.72

ammed

-0.71

 wrapped

-0.67

 diseng

-0.63

anasia

-0.63

 dearly

-0.60

 estranged

-0.60

nor

-0.59

 nowhere

-0.59

 bullied

-0.59

POSITIVE LOGITS

Rank

0.91

Notable

0.88

Pros

0.86

GROUND

0.86

Below

0.85

Names

0.84

LIST

0.82

Advertisement

0.81

Sources

0.81

Article

0.80

Activations Density 0.331%

phrases related to instructions or tips

markers indicating the beginning or end of segments in a document

No Comments

No Known Activations