INDEX

Explanations

negations and related phrases indicating the absence or unlikelihood of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

be

-1.35

 soient

-1.26

be

-1.24

Be

-1.18

Be

-1.10

 siano

-0.91

BE

-0.88

 sejam

-0.86

 aient

-0.83

 puissent

-0.80

POSITIVE LOGITS

 deserve

0.93

 need

0.89

 belong

0.88

 seem

0.84

SourceChecksum

0.84

owe

0.76

 nahilalakip

0.76

LookAnd

0.76

 want

0.75

 know

0.73

Activations Density 0.244%

negations and related phrases indicating the absence or unlikelihood of something

No Comments

No Known Activations