INDEX

Explanations

instances of dialogue and questions

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

expressions of questioning and affirming self-awareness or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

DetailComponent

-0.52

StoredProcedure

-0.51

urbing

-0.47

swag

-0.46

addView

-0.45

))=\

-0.45

SourceChecksum

-0.44

╚

-0.44

-0.43

):=\

-0.43

POSITIVE LOGITS

AddTagHelper

0.84

 EconPapers

0.81

 correctes

0.78

Personendaten

0.74



0.71

JpaRepository

0.68

ponses

0.68

Xna

0.67

сылкі

0.67

tagHelperRunner

0.66

Activations Density 0.275%

instances of dialogue and questions

expressions of questioning and affirming self-awareness or statements

No Comments

No Known Activations