INDEX

Explanations

references to conditions or criteria in a research or procedural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

altar

-0.70

 onResume

-0.64

 <<<<<<<<<<<<<<

-0.61

AutoScaleMode

-0.60

 BoxFit

-0.59

WithIOException

-0.57

quec

-0.57

انيف

-0.56

ImageContext

-0.55

ThemeOverlay

-0.54

POSITIVE LOGITS

 Seeder

0.76

</h6>

0.64

RenderAtEndOf

0.60

</th>

0.58

</h4>

0.57

erover

0.56

 Poincar

0.54

[toxicity=0]

0.54

 letti

0.54

Activations Density 0.175%

references to conditions or criteria in a research or procedural context

No Comments

No Known Activations