INDEX

Explanations

notable or noteworthy occurrences or features

oai_token-act-pair · gpt-3.5-turbo

instances of the word "notable" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hell

-0.83

prep

-0.81

©¶æ

-0.77

cock

-0.74

ole

-0.72

door

-0.70

iland

-0.69

emy

-0.69

alyst

-0.68

claimer

-0.68

POSITIVE LOGITS

 exception

0.97

 exceptions

0.94

 absence

0.93

 absent

0.93

 accomplishments

0.90

 landmarks

0.87

Notable

0.84

 feats

0.83

 accomplishment

0.83

 feat

0.82

Activations Density 0.056%

notable or noteworthy occurrences or features

instances of the word "notable" or related terms

No Comments

No Known Activations