INDEX

Explanations

words related to monsters, demons, and paranormal entities

oai_token-act-pair · gpt-3.5-turbo

references to monstrous or supernatural entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.84

actionDate

-0.81

displayText

-0.79

 Values

-0.77

 majors

-0.71

 GOODMAN

-0.71

Recommend

-0.68

rences

-0.68

 Coverage

-0.68

Effective

-0.68

POSITIVE LOGITS

 humanoid

1.05

 lair

1.00

atos

0.99

 menace

0.96

 Cthulhu

0.96

 invading

0.95

 monster

0.95

 lurking

0.94

 Scorp

0.93

 Cerberus

0.93

Activations Density 0.478%

words related to monsters, demons, and paranormal entities

references to monstrous or supernatural entities

No Comments

No Known Activations