INDEX

Explanations

phrases indicating deviation or departure from expected norms

oai_token-act-pair · gpt-3.5-turbo

critical evaluations or assessments of artistic works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

illance

-0.82

 mobilization

-0.78

 mobil

-0.76

 inaug

-0.75

kefeller

-0.73

 arrangements

-0.71

 mobilized

-0.70

amorph

-0.70

Ã¨re

-0.70

ipal

-0.69

POSITIVE LOGITS

 Personally

1.25

Personally

1.25

Honestly

1.10

 Honestly

1.07

 Nope

0.92

 Whilst

0.92

 cringe

0.89

 Regardless

0.87

Firstly

0.87

 negativity

0.87

Activations Density 0.986%

phrases indicating deviation or departure from expected norms

critical evaluations or assessments of artistic works

No Comments

No Known Activations