INDEX

Explanations

phrases indicating uncertainty or anticipation of future events

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate certainty or uncertainty about future events

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

 Hitch

-0.63

irmation

-0.61

 audits

-0.60

reports

-0.60

Â¶

-0.58

 corps

-0.58

 Manhattan

-0.57

rites

-0.57

 relocation

-0.57

Footnote

-0.57

POSITIVE LOGITS

 happening

1.17

 wrong

0.90

 occurring

0.85

 done

0.84

 meant

0.79

 gonna

0.75

wrong

0.75

 transpired

0.74

 going

0.73

 happened

0.72

Activations Density 0.109%

phrases indicating uncertainty or anticipation of future events

phrases that indicate certainty or uncertainty about future events

No Comments

No Known Activations