INDEX

Explanations

phrases containing specific locations or directions

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases related to location or context

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

é¾įåĸļå£«

-0.77

owship

-0.77

ername

-0.72

INESS

-0.72

Based

-0.69

 ORDER

-0.68

dule

-0.67

CONT

-0.67

Guide

-0.67

ãĥģ

-0.67

POSITIVE LOGITS

etc

0.80

 example

0.75

 distant

0.73

 particular

0.72

 toddlers

0.71

 hurricanes

0.68

tow

0.67

 periphery

0.67

 steroids

0.65

 starters

0.65

Activations Density 0.543%

phrases containing specific locations or directions

prepositions and phrases related to location or context

No Comments

No Known Activations