INDEX

Explanations

instances of direct or indirect authority figures engaging in controversies or conflicts

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" 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 @ 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

grounds

-0.89

Arcade

-0.79

markets

-0.77

 Accessories

-0.76

cells

-0.76

Examples

-0.74

tarians

-0.74

awei

-0.73

quickShipAvailable

-0.72

 Cases

-0.71

POSITIVE LOGITS

 slew

1.08

 nonexistent

1.00

 handful

0.99

 longstanding

0.96

 multitude

0.96

 plethora

0.95

 portion

0.95

 loophole

0.93

 swath

0.92

 perceived

0.90

Activations Density 0.283%

instances of direct or indirect authority figures engaging in controversies or conflicts

the indefinite article "a" in various contexts

No Comments

No Known Activations