INDEX

Explanations

words related to academic degrees

oai_token-act-pair · gpt-3.5-turbo

references to various academic degrees

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

theless

-0.75

miah

-0.66

gm

-0.64

\":

-0.63

ãĤ»

-0.63

oids

-0.61

 Tanz

-0.61

BY

-0.61

 Tosh

-0.61

 stretched

-0.60

POSITIVE LOGITS

ploma

0.96

 Degree

0.94

 degree

0.94

 degrees

0.93

uates

0.91

 dissertation

0.85

Deg

0.85

rees

0.83

degree

0.81

angan

0.79

Activations Density 0.015%

words related to academic degrees

references to various academic degrees

No Comments

No Known Activations