INDEX

Explanations

verbs related to mental processes, specifically regarding thinking or considering something

oai_token-act-pair · gpt-3.5-turbo

phrases that lead to concepts or ideas that can be elaborated upon

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mp

-0.71

sonian

-0.62

pite

-0.61

iability

-0.61

 slightest

-0.59

ui

-0.59

isma

-0.58

SPONSORED

-0.58

soever

-0.57

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.57

POSITIVE LOGITS

 ourselves

0.77

 ways

0.72

 oneself

0.71

illard

0.70

 quitting

0.69

 yourself

0.69

abel

0.65

 yourselves

0.64

agine

0.62

 wanting

0.62

Activations Density 0.041%

verbs related to mental processes, specifically regarding thinking or considering something

phrases that lead to concepts or ideas that can be elaborated upon

No Comments

No Known Activations