INDEX

Explanations

words related to locks and locking mechanisms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lock."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

aukee

-0.70

ãĤ¡

-0.66

aced

-0.65

issance

-0.64

PsyNetMessage

-0.62

LV

-0.62

opausal

-0.62

resso

-0.60

ANI

-0.60

NAT

-0.60

POSITIVE LOGITS

picking

1.09

heed

1.05

 lock

0.96

pick

0.93

 locks

0.91

lear

0.82

lock

0.82

locking

0.79

door

0.78

master

0.74

Activations Density 0.009%

words related to locks and locking mechanisms

occurrences of the word "lock."

No Comments

No Known Activations