INDEX

Explanations

proper nouns or specific names of events, technologies, organizations, or terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "known" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

hibition

-0.75

rentice

-0.70

IRO

-0.64

 fixation

-0.63

itiveness

-0.63

raining

-0.63

psey

-0.63

uda

-0.62

lot

-0.59

olicy

-0.59

POSITIVE LOGITS

 collectively

0.99

 euphem

0.91

 abbrevi

0.89

 alternatively

0.86

 locally

0.86

as

0.86

 acronym

0.84

 internally

0.82

 pseudonym

0.80

 coll

0.80

Activations Density 0.034%

proper nouns or specific names of events, technologies, organizations, or terms

occurrences of the word "known" in various contexts

No Comments

No Known Activations