INDEX

Explanations

names related to the name "Kent"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Kent"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-1.07

thood

-0.90

 behavi

-0.81

viation

-0.80

BOOK

-0.77

SHIP

-0.75

estyles

-0.74

mble

-0.71

issance

-0.71

ciation

-0.71

POSITIVE LOGITS

rell

0.97

 Kent

0.96

 Somers

0.87

mare

0.85

wood

0.84

alus

0.84

ucky

0.84

 Dover

0.79

ree

0.78

ridge

0.76

Activations Density 0.011%

names related to the name "Kent"

mentions of the name "Kent"

No Comments

No Known Activations