INDEX

Explanations

programming constructs and method invocations related to data structures and file handling

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

Code-related tokens and symbols

np_acts-logits-general · gemini-2.0-flash

function/variable assignments

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.93

-0.84

-0.78

so

-0.77

-0.75

<eos>

-0.75

-0.74

POSITIVE LOGITS

 myſelf

2.10

 himſelf

1.85

 themſelves

1.82

 purpoſe

1.77

 ―――――

1.75

 Anſ

1.74

ſelves

1.70

 doubtnut

1.70

 Jefus

1.70

 raiſ

1.70

Activations Density 0.266%

programming constructs and method invocations related to data structures and file handling

Code-related tokens and symbols

function/variable assignments

No Comments

No Known Activations