INDEX

Explanations

terms related to summaries or overviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Klee

-0.73

 Lins

-0.67

 sebagainya

-0.63

 ostavi

-0.61

 Kenn

-0.59

Carn

-0.58

-0.57

ch

-0.57

rop

-0.57

Jaz

-0.57

POSITIVE LOGITS

summary

1.16

 summaries

1.15

maries

1.08

 summary

1.05

 Summaries

1.04

SUMMARY

0.99

 myſelf

0.92

tonsoft

0.88

 Summary

0.86

 faſt

0.86

Activations Density 0.044%

terms related to summaries or overviews

No Comments

No Known Activations