INDEX

Explanations

names or keywords related to specific entities, possibly with a focus on names that are not common nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 STATS

-0.68

 innocence

-0.60

 Cinderella

-0.60

 meditation

-0.60

Reviewer

-0.59

Ou

-0.59

Constructed

-0.58

LSD

-0.58

 attendant

-0.58

 preservation

-0.58

POSITIVE LOGITS

edo

1.08

oshenko

1.04

obl

0.87

nel

0.87

asury

0.86

opot

0.80

hiba

0.80

arkin

0.79

oren

0.79

flix

0.78

Activations Density 0.097%

names or keywords related to specific entities, possibly with a focus on names that are not common nouns

proper nouns and specific names

No Comments

No Known Activations