INDEX

Explanations

computer code snippets

oai_token-act-pair · gpt-3.5-turbo

numerical values and measurements related to performance or effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 presumably

-0.67

 spurious

-0.67

 interference

-0.67

umably

-0.65

 inflation

-0.64

 undermin

-0.61

uca

-0.61

 extrad

-0.60

 Ratt

-0.60

 unexplained

-0.60

POSITIVE LOGITS

Learn

1.09

Features

0.96

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.91

ÂłÂłÂł

0.82

Discover

0.81

 Specifications

0.81

Ingredients

0.80

Supported

0.80

âĸ¬âĸ¬

0.79

rawdownloadcloneembedreportprint

0.77

Activations Density 0.448%

computer code snippets

numerical values and measurements related to performance or effectiveness

No Comments

No Known Activations