INDEX

Explanations

keywords related to the beverage "coke."

oai_token-act-pair · gpt-3.5-turbo

terms related to gambling or games of chance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ohn

-0.75

 Gerr

-0.75

£ı

-0.74

cv

-0.72

 Shad

-0.72

 skelet

-0.71

 Contrast

-0.70

Vog

-0.70

İĭ

-0.70

 Aure

-0.70

POSITIVE LOGITS

 clinics

0.93

 machines

0.90

 donation

0.87

 prescriptions

0.84

 sessions

0.84

 pills

0.82

 clinic

0.82

 subscriptions

0.81

 booths

0.79

 cartridges

0.79

Activations Density 0.223%

keywords related to the beverage "coke."

terms related to gambling or games of chance

No Comments

No Known Activations