INDEX

Explanations

numerical ranges or quantities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate ranges or estimates in quantities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 linked

-0.60

ESE

-0.58

 trave

-0.58

 Dynamics

-0.57

 distur

-0.57

 Accessed

-0.56

idia

-0.55

 relates

-0.55

ife

-0.54

 devise

-0.53

POSITIVE LOGITS

 dozen

0.93

 half

0.86

dozen

0.84

 eighty

0.84

0.83

 seventy

0.82

0.81

0.80

Activations Density 0.205%

numerical ranges or quantities

phrases that indicate ranges or estimates in quantities

No Known Activations