INDEX

Explanations

instances where something is being demonstrated or shown

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "demonstrate" and its variations

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

lake

-0.74

leans

-0.74

ole

-0.74

alez

-0.71

ishops

-0.65

etheless

-0.63

cloth

-0.63

zone

-0.63

line

-0.63

pour

-0.62

POSITIVE LOGITS

arov

0.82

 feats

0.80

anooga

0.79

 demonstrating

0.73

ments

0.73

manship

0.70

Â¯Â¯

0.70

 displays

0.69

ered

0.68

 prowess

0.68

Activations Density 0.033%

instances where something is being demonstrated or shown

occurrences of the word "demonstrate" and its variations

No Comments

No Known Activations