INDEX

Explanations

mentions of students or student-related activities

oai_token-act-pair · gpt-3.5-turbo

references to students

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

UTERS

-0.70

 bilateral

-0.66

rous

-0.65

 Cape

-0.64

bis

-0.63

 Shore

-0.62

 brisk

-0.59

 magn

-0.58

 subdu

-0.58

 leash

-0.57

POSITIVE LOGITS

hip

1.01

Students

0.99

student

0.93

 students

0.92

hips

0.87

uates

0.87

girls

0.82

 Students

0.82

boys

0.80

tu

0.80

Activations Density 0.029%

mentions of students or student-related activities

references to students

No Comments

No Known Activations