INDEX

Explanations

string contents that signify error codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 myſelf

-0.94

PWN

-0.94

 كومونز

-0.87

 Brenn

-0.83

 roulant

-0.83

 ſame

-0.81

)+"

-0.81

 ogóle

-0.79

 fevere

-0.79

 raiſ

-0.77

POSITIVE LOGITS

1.20

 Humphries

1.02

いる

0.97

::::::::

0.97

0.94

iwa

0.87

:-

0.86

 Ayres

0.82

sertation

0.82

허

0.82

Activations Density 0.097%

string contents that signify error codes

No Comments

No Known Activations