INDEX

Explanations

positive or affirmative statements

oai_token-act-pair · gpt-3.5-turbo

phrases and expressions of personal opinions or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ESE

-0.84

*/(

-0.77

otiation

-0.76

aptic

-0.75

umbnails

-0.75

toggle

-0.72

ICLE

-0.71

-0.70

ourses

-0.70

ãĤº

-0.70

POSITIVE LOGITS

 impossible

1.12

 hilarious

1.11

 funny

1.11

 gonna

1.10

 cool

1.07

 unbeat

1.06

 cute

1.05

 alright

1.04

 crazy

1.04

 inevitable

1.04

Activations Density 0.138%

positive or affirmative statements

phrases and expressions of personal opinions or evaluations

No Comments

No Known Activations