INDEX

Explanations

phrases indicating ability or possibility

oai_token-act-pair · gpt-3.5-turbo

conditional phrases that express the ability or possibility of action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

senal

-0.76

fired

-0.64

 raged

-0.63

Choice

-0.63

 Strikes

-0.62

 Politics

-0.62

anamo

-0.61

Ez

-0.61

ELD

-0.61

 behavi

-0.60

POSITIVE LOGITS

't

1.62

 afford

1.45

 convince

1.15

 muster

1.09

 persuade

1.05

 manage

1.05

 locate

1.02

 find

0.97

 tolerate

0.94

 reproduce

0.93

Activations Density 0.094%

phrases indicating ability or possibility

conditional phrases that express the ability or possibility of action

No Comments

No Known Activations