INDEX

Explanations

terms related to "load" or "loading" in various contexts

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

 Enix

-0.66

typeorm

-0.62

انتهای

-0.62

 AssemblyTitle

-0.60

CodeAnalysis

-0.60

 Svensk

-0.60

 示例

-0.59

CrossRef

-0.58

SequentialGroup

-0.57

+#+#

-0.56

POSITIVE LOGITS

unload

1.02

loads

1.02

 loads

1.01

 Loads

1.01

LOAD

0.98

 Load

0.95

 unload

0.94

 load

0.94

 LOAD

0.89

load

0.88

Activations Density 0.085%

terms related to "load" or "loading" in various contexts

No Comments

No Known Activations