INDEX

Explanations

phrases related to being restricted or confined

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "locked"

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

lus

-0.87

resso

-0.83

annis

-0.71

lication

-0.70

arenthood

-0.67

umbn

-0.67

esan

-0.66

article

-0.65

mony

-0.65

nor

-0.64

POSITIVE LOGITS

picking

0.93

 locked

0.85

locked

0.83

 recess

0.77

heed

0.76

lock

0.72

 lock

0.71

locking

0.71

 horns

0.71

 fist

0.69

Activations Density 0.011%

phrases related to being restricted or confined

occurrences of the word "locked"

No Comments

No Known Activations