INDEX

Explanations

phrases related to a specific type or category of something

oai_token-act-pair · gpt-3.5-turbo

phrases that express types or categories of things

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

oons

-0.84

nets

-0.80

inches

-0.78

ials

-0.77

 Sands

-0.76

andals

-0.74

ulations

-0.73

encers

-0.72

mins

-0.72

ues

-0.71

POSITIVE LOGITS

 poetic

0.83

 reckoning

0.82

 resemblance

0.80

 limbo

0.80

 equilibrium

0.77

 thing

0.76

 existential

0.76

 magic

0.75

 sleeper

0.74

 niche

0.74

Activations Density 0.044%

phrases related to a specific type or category of something

phrases that express types or categories of things

No Comments

No Known Activations