INDEX

Explanations

proper nouns related to specific individuals or locations

oai_token-act-pair · gpt-3.5-turbo

terms related to specific characters or entities, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

enegger

-0.99

dimensional

-0.77

rophic

-0.77

astered

-0.75

oggles

-0.70

uminati

-0.70

body

-0.69

otropic

-0.68

ract

-0.64

stakes

-0.63

POSITIVE LOGITS

 Sana

1.06

 Aman

0.86

ql

0.84

enta

0.81

adan

0.80

ignt

0.79

Ò

0.78

egu

0.77

egal

0.72

uine

0.72

Activations Density 0.011%

proper nouns related to specific individuals or locations

terms related to specific characters or entities, particularly names and locations

No Comments

No Known Activations