INDEX

Explanations

phrases related to discussions, explanations, and categorizations involving specific terms and concepts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence of complex or legalistic language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

waukee

-0.64

ipeg

-0.60

 Hobby

-0.57

ÃĥÃĤ

-0.55

Merit

-0.55

 Hutch

-0.54

 starved

-0.54

 Alive

-0.53

Watch

-0.53

 rampage

-0.53

POSITIVE LOGITS

 acron

0.88

"(

0.87

 acronym

0.85

"-

0.85

 initials

0.84

"+

0.82

 wording

0.79

 indicating

0.78

 suffix

0.77

 alphabet

0.76

Activations Density 0.865%

phrases related to discussions, explanations, and categorizations involving specific terms and concepts

phrases indicating the presence of complex or legalistic language

No Comments

No Known Activations