INDEX

Explanations

personal pronouns followed by words indicating actions or situations

oai_token-act-pair · gpt-3.5-turbo

repeated references to the word "we."

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

Pwr

-0.76

trak

-0.69

 Publication

-0.67

oute

-0.66

 Mehran

-0.65

fleet

-0.60

fect

-0.59

bay

-0.59

cart

-0.58

 Watt

-0.57

POSITIVE LOGITS

're

1.12

IRD

0.94

asel

0.92

aning

0.92

athered

0.89

selves

0.85

asley

0.84

eping

0.84

bsite

0.83

've

0.82

Activations Density 0.225%

personal pronouns followed by words indicating actions or situations

repeated references to the word "we."

No Comments

No Known Activations