INDEX

Explanations

words containing the suffix "ing"

oai_token-act-pair · gpt-3.5-turbo

instances of the abbreviation "AP" or contexts related to various forms of media and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 referen

-0.80

 Haas

-0.70

 Guerrero

-0.64

AUD

-0.62

 Guatem

-0.61

 Sloan

-0.61

 proport

-0.60

::::::::

-0.60

ciating

-0.60

ufact

-0.60

POSITIVE LOGITS

auts

0.73

 Dragonbound

0.73

endas

0.73

rees

0.71

edge

0.69

roots

0.69

urga

0.68

forest

0.67

oths

0.67

antis

0.67

Activations Density 0.602%

words containing the suffix "ing"

instances of the abbreviation "AP" or contexts related to various forms of media and entertainment

No Comments

No Known Activations