INDEX

Explanations

keywords associated with speeches and speaking events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

సు

-0.70

 متعلقه

-0.68

 resourceCulture

-0.59

 CreateTagHelper

-0.57

 HasFactory

-0.57

 notare

-0.56

 Metacritic

-0.55

DataAnnotations

-0.55

tagHelperRunner

-0.55

 Screenshots

-0.53

POSITIVE LOGITS

 speech

2.15

 speeches

1.98

 Speech

1.72

speech

1.72

 speaking

1.65

 Speeches

1.61

 speakers

1.60

 speaker

1.59

Speech

1.55

 SPEECH

1.53

Activations Density 0.395%

keywords associated with speeches and speaking events

No Comments

No Known Activations