INDEX

Explanations

multiple types of reference identifiers and keywords related to fictional categories and programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.66

%;

-0.64

。】

-0.61

expandindo

-0.60

</h6>

-0.59

）』

-0.57

«

-0.56

)]

-0.56

“

-0.56

Diwedd

-0.55

POSITIVE LOGITS

」

1.97

",

1.96

1.89

”

1.86

".

1.77

”,

1.74

")

1.61

”.

1.60

";

1.53

":

1.53

Activations Density 2.574%

multiple types of reference identifiers and keywords related to fictional categories and programming context

No Comments

No Known Activations