INDEX

Explanations

legislative-related terms and phrases

oai_token-act-pair · gpt-3.5-turbo

references to legislative processes and activities

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

strap

-0.82

thritis

-0.77

 Valiant

-0.75

kick

-0.73

PLIED

-0.73

resp

-0.72

 Kinnikuman

-0.71

 Carbuncle

-0.71

ailable

-0.70

close

-0.70

POSITIVE LOGITS

otine

0.94

interstitial

0.93

atures

0.87

 legislative

0.83

 halls

0.81

 appropriations

0.80

 councill

0.80

 redist

0.79

 enforcement

0.79

 instit

0.78

Activations Density 0.008%

legislative-related terms and phrases

references to legislative processes and activities

No Comments

No Known Activations