INDEX

Explanations

terms related to something being independent of something else

oai_token-act-pair · gpt-3.5-turbo

instances of the word "independent"

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

risome

-0.87

 Nieto

-0.85

frey

-0.84

mers

-0.84

ttp

-0.81

amac

-0.79

itual

-0.73

days

-0.71

INESS

-0.70

oran

-0.70

POSITIVE LOGITS

 minded

1.06

 contractor

0.98

 contractors

0.91

lect

0.79

 independent

0.76

 outlet

0.75

 corrobor

0.74

 counsel

0.74

 verification

0.73

 sourcing

0.72

Activations Density 0.014%

terms related to something being independent of something else

instances of the word "independent"

No Comments

No Known Activations