INDEX

Explanations

descriptions of things being concentrated in a particular place or group

oai_token-act-pair · gpt-3.5-turbo

instances of the word "concentrated" or its variations, indicating focus or accumulation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

named

-0.77

ne

-0.75

quel

-0.74

conduct

-0.71

posted

-0.71

anne

-0.70

look

-0.70

aired

-0.69

clad

-0.68

him

-0.68

POSITIVE LOGITS

 concentrated

0.91

 concentration

0.88

 concent

0.77

 concentrating

0.77

 concentrate

0.74

ency

0.74

 Concent

0.73

iple

0.73

herry

0.73

 juices

0.72

Activations Density 0.022%

descriptions of things being concentrated in a particular place or group

instances of the word "concentrated" or its variations, indicating focus or accumulation

No Comments

No Known Activations