INDEX

Explanations

mentions of real or practical concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of reality or legitimacy

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

cellent

-0.80

alian

-0.79

sometimes

-0.76

arettes

-0.74

atri

-0.70

cius

-0.70

asso

-0.70

ð

-0.70

VL

-0.69

atically

-0.69

POSITIVE LOGITS

 whatsoever

1.24

 explanation

1.11

 indication

0.97

 affiliation

0.96

nor

0.96

 obligation

0.96

 reason

0.94

 motive

0.93

 repercussions

0.93

 recourse

0.93

Activations Density 0.203%

mentions of real or practical concepts

terms related to the concept of reality or legitimacy

No Comments

No Known Activations