INDEX

Explanations

numbers and technical terms related to hardware and data specifications

oai_token-act-pair · gpt-3.5-turbo

numerical data and measurements within a context

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

irie

-0.74

yssey

-0.68

 Balk

-0.67

idon

-0.65

 strat

-0.62

 Galile

-0.61

 medi

-0.60

ihu

-0.60

urer

-0.60

arya

-0.60

POSITIVE LOGITS

0.71

cf

0.70

ottest

0.70

0.69

Â±

0.68

0.67

Activations Density 0.243%

numbers and technical terms related to hardware and data specifications

numerical data and measurements within a context

No Comments

No Known Activations