INDEX

Explanations

mentions related to the term 'Gorilla'

oai_token-act-pair · gpt-3.5-turbo

mentions of "Gorilla" or "Gor."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.70

BRE

-0.69

 PATH

-0.69

Constructed

-0.68

 BART

-0.68

Quotes

-0.65

 Flight

-0.64

payer

-0.64

 Dispatch

-0.63

Attempts

-0.62

POSITIVE LOGITS

izont

1.32

achev

1.23

vernment

1.00

aband

0.95

ongyang

0.92

illian

0.90

ideon

0.87

ror

0.85

ascus

0.84

illa

0.83

Activations Density 0.019%

mentions related to the term 'Gorilla'

mentions of "Gorilla" or "Gor."

No Comments

No Known Activations