INDEX

Explanations

names and keywords related to various individuals and locations

oai_token-act-pair · gpt-3.5-turbo

proper names and terms associated with individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 eleph

-0.89

 Draco

-0.83

Haz

-0.81

Tob

-0.80

Taj

-0.80

Raz

-0.77

Kaz

-0.77

 Takeru

-0.77

Zot

-0.71

 bombed

-0.71

POSITIVE LOGITS

Thumbnail

0.92

ual

0.85

iver

0.80

amber

0.77

imum

0.77

BN

0.73

mer

0.71

ivot

0.71

UAL

0.71

pen

0.71

Activations Density 0.278%

names and keywords related to various individuals and locations

proper names and terms associated with individuals or entities

No Comments

No Known Activations