INDEX

Explanations

mentions of uncertainty and self-identification

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "I'm" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

aneers

-0.71

 Skydragon

-0.63

rouse

-0.61

Gap

-0.60

 Ensure

-0.57

 Bench

-0.57

Roh

-0.57

Pow

-0.57

Poc

-0.57

 Labrador

-0.56

POSITIVE LOGITS

agine

1.18

 gonna

0.98

umbai

0.95

ortal

0.95

selves

0.94

mediately

0.89

ighty

0.89

ael

0.88

initely

0.86

 glad

0.79

Activations Density 0.031%

mentions of uncertainty and self-identification

the presence of the word "I'm" in various contexts

No Comments

No Known Activations