INDEX

Explanations

words related to physical objects and actions happening to them

oai_token-act-pair · gpt-3.5-turbo

specific nouns and technical terms related to mechanisms and structures

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

Ranked

-0.75

;;;;

-0.74

 Helpful

-0.67

Interested

-0.67

 Know

-0.66

ï¸

-0.65

Own

-0.65

ECA

-0.62

 Ranked

-0.62

edIn

-0.62

POSITIVE LOGITS

 disappears

1.08

iest

0.93

 becomes

0.93

osphere

0.87

 ceases

0.85

 explodes

0.84

 goes

0.84

 portion

0.83

 fades

0.83

 wasn

0.83

Activations Density 0.664%

words related to physical objects and actions happening to them

specific nouns and technical terms related to mechanisms and structures

No Comments

No Known Activations