INDEX

Explanations

occurrences of the word "redd" or "QR" in the text

oai_token-act-pair · gpt-3.5-turbo

references to the character "Red" or related terms in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Palest

-0.76

 Trials

-0.74

 Strauss

-0.73

 DRAG

-0.70

ATP

-0.66

lag

-0.66

 GROUP

-0.66

Xi

-0.64

 Phant

-0.63

displayText

-0.63

POSITIVE LOGITS

iquette

1.08

 redd

1.04

itor

0.98

redd

0.93

itory

0.93

 Redd

0.89

itors

0.88

isco

0.87

ington

0.86

eteen

0.85

Activations Density 0.004%

occurrences of the word "redd" or "QR" in the text

references to the character "Red" or related terms in a specific context

No Comments

No Known Activations