INDEX

Explanations

references to photography or photographers

oai_token-act-pair · gpt-3.5-turbo

terms related to photography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hurst

-0.78

zinski

-0.76

steen

-0.71

soType

-0.69

plings

-0.69

adder

-0.69

speech

-0.68

emonic

-0.67

pling

-0.64

plain

-0.63

POSITIVE LOGITS

 gallery

1.13

 photographer

1.08

 Photographer

1.08

 photographers

1.07

 portraits

1.06

 photography

1.05

 photograp

1.05

 photographed

1.04

 galleries

1.01

ynthesis

1.00

Activations Density 0.072%

references to photography or photographers

terms related to photography

No Comments

No Known Activations