INDEX

Explanations

Twitter posts with accompanying images

oai_token-act-pair · gpt-3.5-turbo

references to pictures

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

ifted

-0.63

 Cambod

-0.62

 confounding

-0.61

edient

-0.61

quartered

-0.61

 continuum

-0.61

 Leilan

-0.60

 clust

-0.60

NetMessage

-0.59

cffff

-0.58

POSITIVE LOGITS

colo

1.04

twitter

0.90

amera

0.85

pic

0.84

pic

0.84

://

0.82

book

0.79

que

0.79

ograph

0.79

ares

0.77

Activations Density 0.008%

Twitter posts with accompanying images

references to pictures

No Comments

No Known Activations