INDEX

Explanations

names of people and locations

oai_token-act-pair · gpt-3.5-turbo

a specific type of separation or transition in the text

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

ecided

-0.74

luster

-0.68

nesday

-0.67

acqu

-0.67

livion

-0.62

terday

-0.62

onto

-0.62

chuk

-0.60

ithub

-0.57

ainment

-0.57

POSITIVE LOGITS

 âĢº

0.74

 WATCHED

0.74

 Â·

0.64

 Photograph

0.62

 largeDownload

0.62

é¾į

0.61

 Files

0.60

 COURT

0.60

 Scenes

0.59

 Profile

0.59

Activations Density 0.213%

names of people and locations

a specific type of separation or transition in the text

No Comments

No Known Activations