INDEX

Explanations

words related to meeting a specific standard or requirement

oai_token-act-pair · gpt-3.5-turbo

terms related to qualification or eligibility criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Gardens

-0.77

 Lans

-0.71

 Torn

-0.71

 Spice

-0.69

eland

-0.66

 wrinkles

-0.63

 drip

-0.63

orah

-0.62

 rook

-0.61

aging

-0.61

POSITIVE LOGITS

ifies

1.05

ifications

1.05

ifiers

1.01

ifying

0.99

itatively

0.95

ifier

0.86

IFIED

0.85

animous

0.84

iotics

0.84

 qualifications

0.81

Activations Density 0.027%

words related to meeting a specific standard or requirement

terms related to qualification or eligibility criteria

No Comments

No Known Activations