INDEX

Explanations

references to corners 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

databind

-0.90

ApiModelProperty

-0.82

świad

-0.76

bekah

-0.76

anyahu

-0.76

 vaisselle

-0.76

MutableLiveData

-0.74

írit

-0.74

thansa

-0.74

Musa

-0.73

POSITIVE LOGITS

 corners

1.72

 corner

1.63

 Corner

1.60

Corner

1.55

 Corners

1.55

 CORNER

1.47

Corners

1.47

corner

1.46

corners

1.45

 CORN

1.19

Activations Density 0.061%

references to corners in various contexts

No Comments

No Known Activations