INDEX

Explanations

patterns of comparison and equivalence in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 similarly

-0.87

similar

-0.77

Similarly

-0.75

 Similarly

-0.74

 Similar

-0.72

Similar

-0.69

 similar

-0.68

Viited

-0.67

 SIMILAR

-0.64

 calendriers

-0.64

POSITIVE LOGITS

 exact

0.86

 ſame

0.82

 sane

0.82

sam

0.82

 self

0.79

 же

0.78

 zelf

0.78

sae

0.77

 samym

0.76

 saine

0.75

Activations Density 0.145%

patterns of comparison and equivalence in descriptions

No Comments

No Known Activations