INDEX

Explanations

phrases related to taking action or making efforts to change or improve something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "make" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.66

 nurs

-0.60

Mub

-0.59

ga

-0.57

 Wick

-0.57

pac

-0.56

br

-0.56

---------

-0.56

 Bung

-0.56

 hops

-0.55

POSITIVE LOGITS

 sure

1.06

hift

0.98

emort

0.84

awaru

0.82

iversal

0.81

solete

0.79

itives

0.78

levard

0.76

urate

0.73

itions

0.72

Activations Density 0.115%

phrases related to taking action or making efforts to change or improve something

occurrences of the word "make" in various contexts

No Comments

No Known Activations