INDEX

Explanations

geographical locations or entities containing the word "Gev" or similar

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ge."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

kefeller

-1.00

icum

-0.89

acca

-0.87

Interstitial

-0.83

iqueness

-0.71

ending

-0.68

netflix

-0.67

idental

-0.67

ended

-0.67

unity

-0.67

POSITIVE LOGITS

hog

1.01

orge

0.93

ORGE

0.92

eks

0.85

ois

0.85

cko

0.84

rer

0.83

orgetown

0.83

orget

0.83

rers

0.79

Activations Density 0.025%

geographical locations or entities containing the word "Gev" or similar

occurrences of the word "ge."

No Comments

No Known Activations