INDEX

Explanations

programming language constructs related to variable assignments and echoing outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 <>",

-0.64

تقاوى

-0.56

 <=",

-0.56

IsContent

-0.55

IVEREF

-0.55

Personendaten

-0.53

 händ

-0.51

mainAxisSize

-0.49

 consultato

-0.49

MigrationBuilder

-0.49

POSITIVE LOGITS

COUVER

0.56

 snippetHide

0.56

principalTable

0.55

íše

0.54

WithIOException

0.54

 rather

0.53

enterOuterAlt

0.52

optarg

0.50

 CreateTagHelper

0.50

artifactId

0.50

Activations Density 0.278%

programming language constructs related to variable assignments and echoing outputs

No Comments

No Known Activations