INDEX

Explanations

university names or abbreviations

oai_token-act-pair · gpt-3.5-turbo

names, terms, or identifiers that are significant within a specific context or narrative

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

webkit

-0.71

©¶æ

-0.71

FontSize

-0.67

ĻĤ

-0.66

kov

-0.66

hetic

-0.66

blance

-0.66

zac

-0.63

scription

-0.63

ubis

-0.63

POSITIVE LOGITS

 Fors

0.64

addle

0.61

 Entered

0.61

hiro

0.60

lear

0.59

 Bord

0.56

0.55

raft

0.55

arters

0.55

wegian

0.55

Activations Density 0.483%

university names or abbreviations

names, terms, or identifiers that are significant within a specific context or narrative

No Comments

No Known Activations