INDEX

Explanations

words related to protection or safeguarding

oai_token-act-pair · gpt-3.5-turbo

terms related to protection and safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ£

-0.80

bold

-0.68

RM

-0.67

mers

-0.64

umo

-0.62

sonian

-0.62

LINE

-0.61

hler

-0.61

leaf

-0.60

rys

-0.59

POSITIVE LOGITS

 afforded

0.93

ively

0.92

iveness

0.84

orship

0.81

folios

0.80

 racket

0.79

ously

0.77

dogs

0.76

aments

0.75

atively

0.75

Activations Density 0.039%

words related to protection or safeguarding

terms related to protection and safety

No Comments

No Known Activations