INDEX

Explanations

variations in information or choices

oai_token-act-pair · gpt-3.5-turbo

conditional statements that depend on variables or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

roo

-0.75

lyn

-0.73

Gil

-0.71

Li

-0.70

together

-0.70

OL

-0.69

-0.68

Gene

-0.67

DragonMagazine

-0.66

="#

-0.66

POSITIVE LOGITS

 circumstances

0.97

 circumstance

0.93

 severity

0.82

 occasion

0.80

 luck

0.75

luck

0.75

 direction

0.74

 availability

0.72

 context

0.71

 prevailing

0.71

Activations Density 0.113%

variations in information or choices

conditional statements that depend on variables or contexts

No Comments

No Known Activations