INDEX

Explanations

references to a specific entity, likely related to the medical field and potentially involving investigations or reports

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Med" or variations related to "Medellin."

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

 innocence

-0.81

cipline

-0.79

âĻ¦

-0.78

AUT

-0.74

ģĸ

-0.74

chnology

-0.72

ãĤ©

-0.71

ãģį

-0.70

!/

-0.69

VALUE

-0.69

POSITIVE LOGITS

ications

1.15

iator

1.06

itations

1.02

iterranean

0.98

iation

0.96

allion

0.96

ient

0.95

icum

0.93

undai

0.92

itate

0.91

Activations Density 0.005%

references to a specific entity, likely related to the medical field and potentially involving investigations or reports

mentions of the word "Med" or variations related to "Medellin."

No Comments

No Known Activations