INDEX

Explanations

references to battle-related terms

oai_token-act-pair · gpt-3.5-turbo

references to battles or conflicts in various contexts

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

elled

-0.73

ophone

-0.73

lect

-0.71

missible

-0.69

ophile

-0.69

itent

-0.68

ĻĤ

-0.68

çīĪ

-0.67

aunder

-0.66

perm

-0.66

POSITIVE LOGITS

 Royale

1.07

halla

1.05

front

0.99

axe

0.99

 Battle

0.90

fleet

0.89

mage

0.84

roy

0.84

cry

0.83

ãĤ¤ãĥĪ

0.81

Activations Density 0.018%

references to battle-related terms

references to battles or conflicts in various contexts

No Comments

No Known Activations