INDEX

Explanations

references to cutting or severing

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

ThroughAttribute

-0.66

ValueStyle

-0.66

phous

-0.66

 propertyName

-0.65

SequentialGroup

-0.65

MENAFN

-0.64

 ainfi

-0.60

,:);

-0.59

complexContent

-0.57

 pharmacie

-0.57

POSITIVE LOGITS

cut

4.88

Cut

4.47

cut

4.38

Cut

4.34

CUT

3.98

 cuts

3.93

CUT

3.79

 Cuts

3.61

cuts

3.56

 cutting

3.41

Activations Density 0.047%

references to cutting or severing

No Comments

No Known Activations