INDEX

Explanations

information about releases or installments in series or franchises

oai_token-act-pair · gpt-3.5-turbo

references to film franchises and their installments

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

nces

-0.89

 nevertheless

-0.77

entimes

-0.71

 elsewhere

-0.69

utterstock

-0.68

ews

-0.67

vana

-0.66

acon

-0.65

inem

-0.65

onday

-0.65

POSITIVE LOGITS

 trilogy

1.18

 series

1.09

series

0.99

 saga

0.98

 Series

0.86

Series

0.81

 dynasty

0.74

 Chain

0.72

 countdown

0.72

 Trilogy

0.72

Activations Density 0.289%

information about releases or installments in series or franchises

references to film franchises and their installments

No Comments

No Known Activations