INDEX

Explanations

ldg characters or symbols representing mathematical operators and expressions in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 pleaſure

-0.75

 viſ

-0.73

 fevere

-0.71

 Monfieur

-0.71

 ſever

-0.70

 defire

-0.67

 purpoſe

-0.66

 deſt

-0.65

 raiſ

-0.64

 ſmall

-0.64

POSITIVE LOGITS

1.72

0.93

tvguidetime

0.88

檚

0.87

ve

0.82

0.78

--*/

0.77

paramref

0.76

0.75

ibatis

0.73

Activations Density 0.090%

ldg characters or symbols representing mathematical operators and expressions in equations

No Comments

No Known Activations