INDEX

Explanations

alphanumeric strings with varied sequences of characters

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to food or culinary themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Frie

-0.65

 Moroc

-0.65

 Seym

-0.65

 Borders

-0.64

Kik

-0.63

 Canary

-0.62

 Instr

-0.61

 Vaugh

-0.59

 Worse

-0.58

Peb

-0.57

POSITIVE LOGITS

lement

0.72

podcast

0.68

0.66

":{"

0.65

0.64

 Profile

0.62

info

0.62

orm

0.60

conom

0.59

tro

0.58

Activations Density 0.267%

alphanumeric strings with varied sequences of characters

words or phrases related to food or culinary themes

No Comments

No Known Activations