INDEX

Explanations

terms related to toxins and their effects

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

toxin, DON

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 calcetines

-0.43

 embaraz

-0.42

queles

-0.40

 cucharadas

-0.38

 opty

-0.37

 nevoie

-0.37

 hoort

-0.37

 voglia

-0.36

 felicità

-0.35

 coraggio

-0.35

POSITIVE LOGITS

 toxin

0.81

toxins

0.77

 toxins

0.76

toxin

0.73

otoxin

0.67

 kasarigan

0.64

ValueStyle

0.62

 ExecuteAsync

0.61

BufferException

0.60

Tox

0.60

Activations Density 0.025%

terms related to toxins and their effects

toxin, DON

No Comments

No Known Activations