INDEX

Explanations

phrases related to image processing

oai_token-act-pair · gpt-3.5-turbo

words related to images and photography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

nen

-0.82

 Rasmussen

-0.81

eanor

-0.78

undai

-0.71

awar

-0.68

ilitary

-0.67

stad

-0.67

arak

-0.67

shore

-0.67

cair

-0.66

POSITIVE LOGITS

 Processing

0.88

RGB

0.82

 codec

0.78

cells

0.77

 processor

0.77

 processors

0.76

processing

0.74

 Output

0.74

 processing

0.73

 grains

0.72

Activations Density 0.086%

phrases related to image processing

words related to images and photography

No Comments

No Known Activations