INDEX

Explanations

words related to negativity or undesirable attributes

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

words with the prefix "un-" that form adjectives describing unexpected or atypical situations.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 propOrder

-0.51

 ſta

-0.44

 ſche

-0.43

ViewImports

-0.42

 potenciales

-0.42

 salvación

-0.41

 redacción

-0.41

 síntesis

-0.41

 déclarations

-0.41

 ſtre

-0.41

POSITIVE LOGITS

un

0.59

unw

0.55

uns

0.53

 unin

0.52

unt

0.52

Uns

0.52

 uncon

0.48

Uns

0.48

Unt

0.48

Unt

0.47

Activations Density 0.141%

words related to negativity or undesirable attributes

words with the prefix "un-" that form adjectives describing unexpected or atypical situations.

No Comments

No Known Activations