INDEX

Explanations

mentions of the word "Snow"

oai_token-act-pair · gpt-3.5-turbo

references to the word "Snow" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ect

-0.83

aneously

-0.74

ista

-0.72

ulous

-0.71

ilar

-0.71

arian

-0.71

arians

-0.69

ations

-0.67

ulously

-0.66

ector

-0.66

POSITIVE LOGITS

flake

1.05

den

0.92

don

0.90

din

0.88

 Leopard

0.84

dropping

0.78

suit

0.77

 Snow

0.77

mobile

0.76

grave

0.71

Activations Density 0.043%

mentions of the word "Snow"

references to the word "Snow" in various contexts

No Comments

No Known Activations