INDEX

Explanations

specific political or academic terminologies and references, including names of organizations and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

StandardCharsets

-0.66

 defStyleAttr

-0.63

 PyTuple

-0.61

NOPQRST

-0.60

 AssemblyCulture

-0.60

styleable

-0.60

FormTagHelper

-0.57

èbres

-0.56

期刊论文

-0.55

ASHINGTON

-0.55

POSITIVE LOGITS

发表于

0.58

atalos

0.52

 Itália

0.46

 gynhyrchwyd

0.45

 entendre

0.45

 salada

0.44

✷

0.44

 مرئيه

0.43

scriptcase

0.43

ftagPool

0.42

Activations Density 0.802%

specific political or academic terminologies and references, including names of organizations and processes

No Comments

No Known Activations