INDEX

Explanations

words related to medical conditions and physical symptoms

oai_token-act-pair · gpt-3.5-turbo

references to different types of ligands and related terms in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Worldwide

-0.71

 Brookings

-0.70

IRED

-0.70

 Riding

-0.70

Discussion

-0.69

 CNBC

-0.68

 Teach

-0.66

DEM

-0.65

 Planning

-0.65

 Neutral

-0.64

POSITIVE LOGITS

lig

1.14

atures

1.14

ature

1.07

aments

0.97

 acids

0.92

 elbows

0.90

 torches

0.86

 corrid

0.85

thening

0.83

glers

0.83

Activations Density 0.011%

words related to medical conditions and physical symptoms

references to different types of ligands and related terms in a scientific context

No Comments

No Known Activations