INDEX

Explanations

positions or rankings described with ordinal numbers

oai_token-act-pair · gpt-3.5-turbo

ordinal numbers and rankings

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

SourceFile

-0.80

someone

-0.71

culosis

-0.70

zsche

-0.69

ËĪ

-0.68

mud

-0.64

kernel

-0.64

jan

-0.64

gone

-0.63

Rust

-0.63

POSITIVE LOGITS

 respectively

1.77

 alike

1.13

 halves

0.92

 respective

0.92

 grades

0.89

 editions

0.89

 administrations

0.89

 versions

0.87

 depending

0.85

 selves

0.85

Activations Density 0.193%

positions or rankings described with ordinal numbers

ordinal numbers and rankings

No Comments

No Known Activations