INDEX

Explanations

terms related to signaling within biological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ImageContext

-0.65

fromnode

-0.62

WriteTagHelper

-0.61

hibe

-0.60

DispatchToProps

-0.60

WebVitals

-0.58

transQ

-0.53

 שוליים

-0.53

ArgsConstructor

-0.53

 McClure

-0.53

POSITIVE LOGITS

 Signals

1.13

 signals

1.10

Signals

0.99

signals

0.93

 signalling

0.82

 signal

0.81

 SIGNAL

0.78

 Sett

0.75

signal

0.74

 signaling

0.72

Activations Density 0.089%

terms related to signaling within biological contexts

No Comments

No Known Activations