INDEX

Explanations

proper nouns, specifically names containing the substring 'Gra' with varying degrees of relevance

oai_token-act-pair · gpt-3.5-turbo

references to the name "Graeme" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ional

-0.80

CPC

-0.76

 Dragonbound

-0.69

nikov

-0.64

 Sands

-0.61

IONS

-0.60

 Leilan

-0.60

payer

-0.60

 Ibid

-0.58

 Corpus

-0.58

POSITIVE LOGITS

ffiti

1.64

veland

1.34

ppa

1.30

veyard

1.30

fters

1.18

vel

1.17

ppe

1.17

eme

1.16

fter

1.15

ppo

1.15

Activations Density 0.036%

proper nouns, specifically names containing the substring 'Gra' with varying degrees of relevance

references to the name "Graeme" and its variations

No Comments

No Known Activations