INDEX

Explanations

references to observation and analysis

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

templateUrl

-0.67

retty

-0.62

jins

-0.59

 functools

-0.58

NegativeButton

-0.56

</h1>

-0.54

</td>

-0.54

 Dalton

-0.53

The

-0.53

kyl

-0.53

POSITIVE LOGITS

 observation

2.19

 observations

2.15

 observe

2.11

 Observation

2.10

 OBSERV

2.10

 observes

2.10

 observed

2.08

 Observations

2.02

 obser

2.00

 Observed

2.00

Activations Density 0.088%

references to observation and analysis

No Comments

No Known Activations