INDEX

Explanations

the word "Wait" or variations of it

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Wait."

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

ãĤº

-0.79

ighter

-0.70

audi

-0.68

reb

-0.68

insula

-0.68

uded

-0.67

jac

-0.66

 Instr

-0.66

phrine

-0.64

ighters

-0.63

POSITIVE LOGITS

wait

0.93

 Wait

0.90

 wait

0.82

 patiently

0.80

ruciating

0.79

eful

0.73

Wait

0.72

resses

0.72

pid

0.70

 Waiting

0.70

Activations Density 0.017%

the word "Wait" or variations of it

instances of the word "Wait."

No Comments

No Known Activations