INDEX

Explanations

technical terms or jargon

oai_token-act-pair · gpt-3.5-turbo

terms and phrases that refer to specific concepts or terminology

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

Ws

-0.71

 Progress

-0.70

igators

-0.69

edient

-0.68

mits

-0.68

 taxp

-0.66

 batches

-0.65

 failures

-0.64

 progressing

-0.64

 incremental

-0.63

POSITIVE LOGITS

 coined

1.44

 shorthand

1.34

 acronym

1.22

 slang

1.21

 synonymous

1.21

 abbre

1.11

 uttered

1.04

 phrases

1.04

 descriptive

1.04

 dictionary

1.02

Activations Density 0.469%

technical terms or jargon

terms and phrases that refer to specific concepts or terminology

No Comments

No Known Activations