INDEX

Explanations

references to tokens used in API requests and authentication processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Phry

-0.86

 Diſ

-0.82

 scro

-0.82

 cohé

-0.82

GLS

-0.81

 Hurricanes

-0.80

 Diri

-0.79

 Heere

-0.79

 Hierarchy

-0.79

 GridLayout

-0.79

POSITIVE LOGITS

 tokens

1.90

 token

1.83

 Token

1.69

 Tokens

1.60

token

1.58

tokens

1.58

Tokens

1.56

jsonwebtoken

1.50

TOKEN

1.49

Token

1.48

Activations Density 0.109%

references to tokens used in API requests and authentication processes

No Comments

No Known Activations