INDEX

Explanations

verbs or phrases indicating that certain information is not provided or specified

oai_token-act-pair · gpt-3.5-turbo

terms related to reporting, documentation, and the availability of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ortment

-0.70

haul

-0.67

itton

-0.63

rahim

-0.59

ennett

-0.59

href

-0.58

redients

-0.57

tnc

-0.56

ggles

-0.56

arms

-0.56

POSITIVE LOGITS

 anymore

1.63

nor

1.35

 anywhere

1.07

 necessarily

0.99

 whatsoever

0.98

yet

0.91

any

0.82

yet

0.81

ktop

0.80

 unless

0.78

Activations Density 0.181%

verbs or phrases indicating that certain information is not provided or specified

terms related to reporting, documentation, and the availability of information

No Comments

No Known Activations