INDEX

Explanations

phrases that indicate a significant change or transformation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate significant transformations or alterations over time

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

mination

-0.75

 DRAGON

-0.72

ç«

-0.69

amina

-0.68

AFB

-0.68

alty

-0.65

hold

-0.64

äºĶ

-0.64

PLIED

-0.64

Vs

-0.63

POSITIVE LOGITS

 dramatically

0.87

 drastically

0.86

amorph

0.84

ĸļ

0.76

 psychiat

0.76

 abruptly

0.74

 radically

0.74

anwhile

0.73

 decisively

0.72

 effected

0.71

Activations Density 0.048%

phrases that indicate a significant change or transformation

phrases that indicate significant transformations or alterations over time

No Comments

No Known Activations