INDEX

Explanations

titles or references to specific volumes or publications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Vol" and its variations, likely indicating a focus on volume numbers in publications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riad

-0.78

 Synd

-0.68

 Pearce

-0.68

 Rampage

-0.66

 Turing

-0.66

merce

-0.63

 Gauntlet

-0.63

 Defenders

-0.60

 Clarkson

-0.60

 Annotations

-0.60

POSITIVE LOGITS

atile

1.36

atility

1.34

untary

1.25

umes

1.20

unte

0.97

leys

0.95

untarily

0.90

cano

0.88

vol

0.84

itionally

0.83

Activations Density 0.016%

titles or references to specific volumes or publications

occurrences of the term "Vol" and its variations, likely indicating a focus on volume numbers in publications

No Comments

No Known Activations