INDEX

Explanations

references to paths and journeys, either literal or metaphorical

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 titulaire

-0.54

 overhang

-0.51

 tiguan

-0.51

apimachinery

-0.50

 Monfieur

-0.50

 asymmetry

-0.49

 Complexes

-0.49

 Cores

-0.49

fej

-0.49

 homogeneity

-0.49

POSITIVE LOGITS

 paths

2.00

 path

1.93

 Paths

1.71

paths

1.66

 Path

1.65

path

1.55

 pathways

1.51

 pathway

1.46

 route

1.44

 routes

1.42

Activations Density 0.320%

references to paths and journeys, either literal or metaphorical

No Comments

No Known Activations