INDEX

Explanations

references to the term "Golden" followed by another word

oai_token-act-pair · gpt-3.5-turbo

references to the "Golden State" or "Golden Gate" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mble

-0.84

ional

-0.82

akeru

-0.80

Ì¶

-0.75

Downloadha

-0.72

igham

-0.71

ithing

-0.71

kers

-0.71

lessly

-0.70

uality

-0.69

POSITIVE LOGITS

 Golden

0.94

Golden

0.90

 golden

0.80

Age

0.77

grass

0.76

thora

0.74

ocious

0.74

pha

0.73

fish

0.72

 Flavoring

0.72

Activations Density 0.004%

references to the term "Golden" followed by another word

references to the "Golden State" or "Golden Gate" in various contexts

No Comments

No Known Activations