INDEX

Explanations

specific tags and annotations used in coding or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-0.84

glTexCoord

-0.69

:✨

-0.62

begingroup

-0.61

 censiti

-0.60

ImageContext

-0.60

 nakalista

-0.59

 ujednoznacz

-0.59

 Anſ

-0.57

UnusedPrivate

-0.57

POSITIVE LOGITS

Gizmos

0.60

 mark

0.52

jsonwebtoken

0.52

 marks

0.51

 outline

0.49

plot

0.49

 marking

0.49

 showing

0.47

 trace

0.47

 plots

0.47

Activations Density 0.044%

specific tags and annotations used in coding or programming contexts

No Comments

No Known Activations