INDEX

Explanations

locations, specifically focusing on places containing "Nev" or "Julia"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations and names, particularly in relation to people or entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Bomber

-0.92

Ali

-0.82

Oil

-0.81

 BASE

-0.79

draft

-0.78

 Shiite

-0.75

Template

-0.73

Lac

-0.71

tm

-0.71

 Tradition

-0.71

POSITIVE LOGITS

Nev

1.98

Nev

1.59

 Julia

1.50

 Gunn

1.34

vind

1.34

AV

1.16

nn

1.15

 Shen

1.13

 vind

1.10

 Neville

1.10

Activations Density 0.062%

locations, specifically focusing on places containing "Nev" or "Julia"

mentions of specific locations and names, particularly in relation to people or entities

No Known Activations