INDEX

Explanations

words and terms associated with prefixes and suffixes in programming or markup languages

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ı

-2.25

¿

-2.08

ĥ½

-2.02

³

-2.00

ĥ

-1.96

ĨĴ

-1.94

---|---

-1.93

§

-1.92

ľĵ

-1.89

¬

-1.88

POSITIVE LOGITS

ston

1.72

ivos

1.69

igent

1.61

het

1.60

stÃ¤

1.58

shot

1.57

ENTIAL

1.54

quote

1.54

park

1.54

smith

1.53

Activations Density 0.010%

words and terms associated with prefixes and suffixes in programming or markup languages

No Comments

No Known Activations