INDEX

Explanations

instructions or directives addressing intended outcomes or improvements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

principalTable

-0.85

 otomatig

-0.66

 EconPapers

-0.65

 comuniques

-0.61

يكب

-0.58

ukone

-0.55

HasIndex

-0.55

Demografie

-0.53

WithIOException

-0.52

UIControlState

-0.51

POSITIVE LOGITS

 date

0.88

sum

0.87

 quote

0.81

 paraphrase

0.81

 summarize

0.80

 recap

0.78

 summarise

0.74

 complicate

0.68

 kasarigan

0.66

sum

0.63

Activations Density 0.125%

instructions or directives addressing intended outcomes or improvements

No Comments

No Known Activations