INDEX

Explanations

phrases related to extracting or extraction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "extract" 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

ndra

-0.82

nd

-0.72

gaard

-0.72

osuke

-0.64

Die

-0.64

die

-0.64

fram

-0.63

ned

-0.62

stand

-0.62

present

-0.61

POSITIVE LOGITS

 extract

0.91

ions

0.87

ract

0.87

 extracting

0.85

racted

0.84

ngth

0.83

 extracted

0.82

 extraction

0.81

 extracts

0.80

raction

0.80

Activations Density 0.014%

phrases related to extracting or extraction

occurrences of the word "extract" and its variations

No Comments

No Known Activations