INDEX

Explanations

terms related to thermal processes and temperature effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ellschaft

-0.58

razine

-0.57

ixote

-0.56

šanai

-0.56

thâu

-0.54

ussian

-0.54

ophila

-0.53

mink

-0.51

ioma

-0.51

 @"";

-0.51

POSITIVE LOGITS

 heat

1.96

 Heat

1.89

 heats

1.78

Heat

1.78

 heating

1.77

heat

1.74

 temperature

1.67

 HEAT

1.66

 heated

1.64

 thermal

1.64

Activations Density 2.606%

terms related to thermal processes and temperature effects

No Comments

No Known Activations