INDEX

Explanations

references to cutting or cuts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

BibitemShut

-0.69

,:);

-0.64

 personne

-0.62

 cias

-0.62

PyExc

-0.61

complexContent

-0.61

PANY

-0.60

WebElementEntity

-0.60

SequentialGroup

-0.59

phous

-0.58

POSITIVE LOGITS

cut

3.97

Cut

3.68

cut

3.64

Cut

3.53

 cuts

3.39

CUT

3.37

CUT

3.17

 Cuts

3.12

cuts

3.10

 cutting

2.81

Activations Density 0.042%

references to cutting or cuts in various contexts

No Comments

No Known Activations