INDEX

Explanations

terms related to applicants or candidates, particularly in the context of selection or application processes

oai_token-act-pair · gpt-3.5-turbo

terminology related to applicants or applicants' status

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

roman

-0.85

 Alps

-0.78

vern

-0.72

feeding

-0.65

pac

-0.65

Alz

-0.64

 Hobby

-0.63

 Charge

-0.63

haul

-0.62

Charge

-0.62

POSITIVE LOGITS

 applicant

1.22

 applicants

1.21

 Applicant

1.06

 contestants

0.87

 applications

0.85

 licenses

0.84

 contestant

0.84

 interviews

0.82

lication

0.81

ele

0.81

Activations Density 0.019%

terms related to applicants or candidates, particularly in the context of selection or application processes

terminology related to applicants or applicants' status

No Comments

No Known Activations