INDEX

Explanations

terms related to cycles or repetitions, particularly in relation to growth or financial models

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

Personensuche

-0.67

帖最后由

-0.61

aarrggbb

-0.58

voorbeeld

-0.55

neurial

-0.54

Становништво

-0.54

gonic

-0.53

rokken

-0.51

 useContext

-0.51

 själ

-0.51

POSITIVE LOGITS

:✨

0.59

❯

0.58

★★★★☆

0.57

GYPT

0.56

ishness

0.55

patra

0.55

hound

0.55

⏪

0.54

Panamoan

0.54

scribers

0.54

Activations Density 0.441%

terms related to cycles or repetitions, particularly in relation to growth or financial models

No Comments

No Known Activations