INDEX

Explanations

instances of the word "accurately" in a document

oai_token-act-pair · gpt-3.5-turbo

terms related to accuracy and fidelity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 inaction

-0.83

 reactions

-0.73

 willingness

-0.72

 taboo

-0.70

 tropes

-0.70

 necessity

-0.70

 contradictions

-0.69

 reaction

-0.67

 favorites

-0.67

 absurdity

-0.67

POSITIVE LOGITS

ãĤ©

1.02

imated

0.96

ufact

0.92

 modeled

0.84

 accurately

0.84

mented

0.81

atered

0.80

 suited

0.80

 represented

0.80

 scratched

0.80

Activations Density 0.013%

instances of the word "accurately" in a document

terms related to accuracy and fidelity

No Comments

No Known Activations