INDEX

Explanations

technical terms and coding syntax related to web development and APIs

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Personendaten

-1.09

SourceChecksum

-0.79

IndentedString

-0.77

InSection

-0.77

MessageOf

-0.77

uxxxx

-0.76

WriteBarrier

-0.75

setVerticalGroup

-0.75

fjspx

-0.74

 EClass

-0.73

POSITIVE LOGITS

 bangsa

0.66

token

0.63

 TOKEN

0.58

 token

0.56

 bytes

0.56

ᶦ

0.55

 Token

0.55

 overras

0.55

Token

0.54

Tokens

0.54

Activations Density 0.036%

technical terms and coding syntax related to web development and APIs

No Known Activations