INDEX

Explanations

terms related to tools and fasteners

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ardes

-0.63

 referrerpolicy

-0.61

streets

-0.55

SuppressLint

-0.55

kloped

-0.54

 Chriftian

-0.52

unrecognized

-0.52

 lenker

-0.52

 Americano

-0.50

NotEqualTo

-0.50

POSITIVE LOGITS

 bolt

0.65

 Pelham

0.63

 bolts

0.63

 Pingback

0.62

bolt

0.61

 Bolt

0.60

ParallelGroup

0.60

 Bolts

0.58

 remb

0.58

 bieber

0.56

Activations Density 2.159%

terms related to tools and fasteners

No Comments

No Known Activations