INDEX

Explanations

mentions of the word "Hunt" or derivations of it

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hun" or its variations in different contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chloride

-0.69

 Byrne

-0.66

 connecting

-0.62

toe

-0.61

 protected

-0.61

 Colossus

-0.61

 responsive

-0.60

 Archangel

-0.60

CBD

-0.58

 Wireless

-0.58

POSITIVE LOGITS

cheon

1.20

ters

1.19

ches

1.15

kered

1.11

zees

1.07

nam

1.04

ched

1.02

eteenth

1.00

chen

0.99

ishers

0.97

Activations Density 0.026%

mentions of the word "Hunt" or derivations of it

occurrences of the word "hun" or its variations in different contexts

No Comments

No Known Activations