INDEX

Explanations

words related to metals, specifically copper

oai_token-act-pair · gpt-3.5-turbo

references to copper

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

arro

-0.74

imaru

-0.72

fare

-0.72

ROR

-0.71

stract

-0.67

inen

-0.67

 Wanted

-0.66

Aid

-0.66

models

-0.65

 Nurs

-0.65

POSITIVE LOGITS

 oxide

0.90

 wool

0.88

 flakes

0.84

 copper

0.84

 piping

0.83

 wire

0.83

 sulf

0.81

ore

0.81

plate

0.79

 pipe

0.78

Activations Density 0.014%

words related to metals, specifically copper

references to copper

No Comments

No Known Activations