INDEX

Explanations

actions related to cleaning or organizing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

hasMany

-0.54

Demografía

-0.51

moveToNext

-0.47

EndProject

-0.47

:✨

-0.46

 Weller

-0.46

 crossorigin

-0.46

XtraGrid

-0.45

RTCK

-0.45

 onData

-0.45

POSITIVE LOGITS

 trimming

1.08

 pruning

1.06

 clipping

1.01

 clipped

0.93

 Trim

0.92

 prune

0.90

 Pruning

0.90

 pruned

0.87

 trims

0.87

 trimmed

0.87

Activations Density 0.474%

actions related to cleaning or organizing

No Comments

No Known Activations