INDEX

Explanations

keywords related to eligibility and qualification criteria

oai_token-act-pair · gpt-3.5-turbo

the word "eligible" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

pread

-0.70

 Alps

-0.67

hunt

-0.65

ijk

-0.65

aura

-0.64

 Principles

-0.64

OVA

-0.64

 Coat

-0.63

-0.62

OTOS

-0.61

POSITIVE LOGITS

 eligible

0.96

untarily

0.95

igible

0.88

uates

0.87

iaries

0.86

eligible

0.85

 claimants

0.81

 qualify

0.80

 borrowers

0.80

 applicants

0.79

Activations Density 0.012%

keywords related to eligibility and qualification criteria

the word "eligible" in various contexts

No Comments

No Known Activations