INDEX

Explanations

verbs related to plot development and character action involving positive or negative interactions.

oai_token-act-pair · gemini-2.0-flash

pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddHtmlAttribute

-0.68

 propOrder

-0.67

AnchorTagHelper

-0.67

localctx

-0.62

webElementXpaths

-0.61

 ones

-0.61

URLException

-0.61

rivit

-0.61

 disambiguazione

-0.60

skjaer

-0.60

POSITIVE LOGITS

him

1.42

him

1.03

us

0.90

lui

0.87

 them

0.85

me

0.75

them

0.75

 henne

0.66

Him

0.63

 honom

0.63

Activations Density 1.779%

verbs related to plot development and character action involving positive or negative interactions.

pronouns

No Comments

No Known Activations