INDEX

Explanations

words related to disqualification or ineligibility

oai_token-act-pair · gpt-3.5-turbo

terms related to disqualification and ineligibility

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

yll

-0.73

ï¸ı

-0.70

Esp

-0.65

elf

-0.64

tons

-0.62

 Lans

-0.62

TPP

-0.61

VID

-0.60

OTOS

-0.60

POSITIVE LOGITS

 disqual

1.31

 disqualified

1.14

ifications

0.95

ifying

0.90

ifiers

0.89

ifies

0.87

ification

0.82

ifier

0.80

mma

0.80

ify

0.76

Activations Density 0.017%

words related to disqualification or ineligibility

terms related to disqualification and ineligibility

No Comments

No Known Activations