INDEX

Explanations

questions in a text

oai_token-act-pair · gpt-3.5-turbo

references to inquiries and questioning

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

ufact

-0.97

axy

-0.79

yss

-0.76

minist

-0.75

oreal

-0.74

 Tycoon

-0.73

rites

-0.72

ensions

-0.69

alty

-0.68

rylic

-0.68

POSITIVE LOGITS

naires

1.40

naire

1.12

 answered

1.08

 posed

1.03

 questions

0.96

 Questions

0.85

 unanswered

0.84

 probing

0.82

 pertaining

0.81

 asked

0.80

Activations Density 0.033%

questions in a text

references to inquiries and questioning

No Comments

No Known Activations