INDEX

Explanations

terms related to secrecy or hidden information

oai_token-act-pair · gpt-3.5-turbo

references to secrecy or confidential matters

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

annis

-0.92

gaard

-0.87

lihood

-0.85

odcast

-0.83

thood

-0.79

©¶æ

-0.78

ulf

-0.77

adjusted

-0.77

Pwr

-0.75

older

-0.75

POSITIVE LOGITS

ariat

1.11

arial

1.07

 ingredient

0.93

 secret

0.87

 sauce

0.85

 stash

0.83

 unfocusedRange

0.82

 handshake

0.81

rets

0.80

 ballot

0.80

Activations Density 0.024%

terms related to secrecy or hidden information

references to secrecy or confidential matters

No Comments

No Known Activations