INDEX

Explanations

terms related to toxicity and toxicological studies

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

Not in Any Lists

No Comments

Negative Logits

PSR

-0.64

><?

-0.63

Cream

-0.60

orance

-0.59

Rag

-0.59

TagHelpers

-0.57

diya

-0.56

Pi

-0.55

Fat

-0.55

omencl

-0.54

POSITIVE LOGITS

RTEX

0.93

WithIOException

0.92

HostException

0.91

 typelib

0.90

RTEE

0.88

 JpaRepository

0.85

 ddelweddau

0.81

awtextra

0.81

principalColumn

0.80

 للاسماء

0.79

Activations Density 1.430%

terms related to toxicity and toxicological studies

No Comments

No Known Activations