INDEX

Explanations

photographs or images in a document

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Photo"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iazep

-0.85

adden

-0.79

uckle

-0.75

ollah

-0.72

ortun

-0.71

otomy

-0.70

ouls

-0.70

resses

-0.70

imore

-0.69

EEK

-0.68

POSITIVE LOGITS

 Gallery

0.92

journal

0.90

 gallery

0.84

 galleries

0.80

 Photo

0.80

 snapped

0.79

 shoots

0.78

 illustration

0.78

 Booth

0.77

 Phot

0.74

Activations Density 0.015%

photographs or images in a document

occurrences of the word "Photo"

No Comments

No Known Activations