INDEX

Explanations

the word "passive"

oai_token-act-pair · gpt-4-turbo

passive or passive-aggressive behaviors mentioned in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "passive" and related terms

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

Issue

-0.75

Lob

-0.73

Grant

-0.71

enegger

-0.69

umble

-0.68

aster

-0.68

ournal

-0.67

src

-0.67

ograp

-0.66

 Grind

-0.66

POSITIVE LOGITS

 Passive

1.16

 passive

1.00

 passively

0.92

 eaves

0.89

 minded

0.86

 intellig

0.84

 reactive

0.80

aggressive

0.76

reet

0.75

ftime

0.74

Activations Density 0.006%

the word "passive"

passive or passive-aggressive behaviors mentioned in text

instances of the word "passive" and related terms

No Comments

No Known Activations