INDEX

Explanations

words related to fluctuations, both positive and negative

oai_token-act-pair · gpt-3.5-turbo

references to positive and negative experiences or outcomes

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

 Portuguese

-0.72

Äĩ

-0.72

EVA

-0.70

Ùĩ

-0.68

ãĥŁ

-0.66

 Mecca

-0.66

Reviewed

-0.63

Art

-0.63

 Gemini

-0.62

Øª

-0.62

POSITIVE LOGITS

ourced

1.30

ourcing

1.23

iders

1.11

ources

1.11

hirt

1.08

laus

1.07

sembly

1.02

ides

1.02

ided

1.01

undown

1.00

Activations Density 0.059%

words related to fluctuations, both positive and negative

references to positive and negative experiences or outcomes

No Comments

No Known Activations