INDEX

Explanations

financial terms like acronyms and job titles

oai_token-act-pair · gpt-3.5-turbo

patterns of numerical or financial data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lets

-0.75

metadata

-0.70

 fortunate

-0.68

jury

-0.61

rounded

-0.60

where

-0.59

falls

-0.59

Thumbnail

-0.58

angered

-0.58

perse

-0.58

POSITIVE LOGITS

1.08

1.05

1.02

0.99

0.97

0.96

0.94

0.93

Activations Density 0.052%

financial terms like acronyms and job titles

patterns of numerical or financial data

No Comments

No Known Activations