INDEX

Explanations

the word "miner" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to miners

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

variable

-0.75

 Liberties

-0.71

ipal

-0.71

WT

-0.70

WD

-0.69

null

-0.69

ending

-0.69

Clo

-0.68

orne

-0.68

 Booth

-0.68

POSITIVE LOGITS

 miner

1.37

 miners

1.32

 corrid

1.11

 mined

0.95

 obser

0.89

 mining

0.88

 crates

0.80

ore

0.78

 gobl

0.78

Merit

0.77

Activations Density 0.007%

the word "miner" or variations of it

references to miners

No Comments

No Known Activations