INDEX

Explanations

words related to naming or mentioning someone or something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "name" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 guiActiveUnfocused

-0.71

stead

-0.66

 NOTICE

-0.61

iment

-0.61

ysc

-0.60

sei

-0.60

pour

-0.59

ismo

-0.59

jp

-0.59

ione

-0.58

POSITIVE LOGITS

 names

1.09

 personalities

0.81

 landmarks

0.80

plates

0.75

names

0.74

 aliases

0.72

gger

0.72

 winners

0.70

 predators

0.70

 culprit

0.69

Activations Density 0.079%

words related to naming or mentioning someone or something

occurrences of the word "name" and its variations

No Comments

No Known Activations