INDEX

Explanations

phrases indicating quantities or numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 MainAxisSize

-0.79

AutoScaleMode

-0.77

 ExecuteAsync

-0.76

principalColumn

-0.75

 ***!

-0.70

ModelAdmin

-0.69

ScopeManager

-0.68

 <=",

-0.67

CodedInputStream

-0.65

POSITIVE LOGITS

 more

3.77

more

3.01

More

2.77

 More

2.67

 MORE

2.60

 mehr

2.57

MORE

2.21

 más

2.19

 lebih

2.14

 więcej

2.08

Activations Density 0.786%

phrases indicating quantities or numerical references

No Comments

No Known Activations