INDEX

Explanations

specific clauses starting with 'which' and describing a feature or attribute

oai_token-act-pair · gpt-3.5-turbo

clauses or phrases that introduce relative clauses or additional information

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 VIDEOS

-0.76

Bed

-0.75

politics

-0.72

MENTS

-0.70

let

-0.65

STE

-0.65

 Baker

-0.62

 Glob

-0.61

grim

-0.60

 Vent

-0.60

POSITIVE LOGITS

soever

0.95

 resulted

0.90

 comprises

0.90

 brings

0.84

 contains

0.83

 attracts

0.83

 consists

0.82

 includes

0.81

 exposes

0.81

 enables

0.80

Activations Density 0.094%

specific clauses starting with 'which' and describing a feature or attribute

clauses or phrases that introduce relative clauses or additional information

No Comments

No Known Activations