INDEX

Explanations

words related to qualification or being qualified

oai_token-act-pair · gpt-3.5-turbo

terms related to qualifications or eligibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Lans

-0.76

 Gardens

-0.73

 Strauss

-0.71

 Sparrow

-0.69

 Spice

-0.67

hattan

-0.67

 wrinkles

-0.67

orah

-0.66

 drip

-0.66

eland

-0.65

POSITIVE LOGITS

ifies

1.05

ifiers

1.02

ifying

1.02

ifications

1.00

ifier

0.88

iotics

0.86

itatively

0.85

animous

0.84

 qualifications

0.82

IFIED

0.81

Activations Density 0.029%

words related to qualification or being qualified

terms related to qualifications or eligibility

No Comments

No Known Activations