INDEX

Explanations

terms related to the state of California

oai_token-act-pair · gpt-3.5-turbo

mentions of California

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

htar

-0.95

chel

-0.82

oscope

-0.71

ahs

-0.70

alsh

-0.70

sworth

-0.69

isen

-0.68

Ott

-0.68

alid

-0.67

umbn

-0.67

POSITIVE LOGITS

 Edison

0.93

Oro

0.93

 Superior

0.79

 Calif

0.78

 Unified

0.77

ISO

0.75

 Penal

0.75

 Springs

0.74

 Coastal

0.71

 Residents

0.70

Activations Density 0.049%

terms related to the state of California

mentions of California

No Comments

No Known Activations