INDEX

Explanations

phrases related to specific items, actions, or events designated for pickup

oai_token-act-pair · gpt-3.5-turbo

specific nouns related to categories or items in a list format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

schild

-0.67

 tremend

-0.65

İĭ

-0.62

ENE

-0.62

 voic

-0.60

 compr

-0.60

 encount

-0.59

 behavi

-0.58

DO

-0.57

IFA

-0.56

POSITIVE LOGITS

ongyang

0.89

ucket

0.80

sburgh

0.79

chedel

0.77

rued

0.73

atche

0.73

 nipples

0.73

uing

0.69

bilt

0.67

Cola

0.67

Activations Density 0.056%

phrases related to specific items, actions, or events designated for pickup

specific nouns related to categories or items in a list format

No Comments

No Known Activations