INDEX

Explanations

phrases related to lifting or removing restrictions

oai_token-act-pair · gpt-3.5-turbo

terms related to lifting restrictions or bans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

present

-0.71

lished

-0.70

errilla

-0.70

ãĥ£

-0.68

 Palin

-0.64

-0.63

 Analy

-0.62

RAL

-0.61

TAG

-0.60

clave

-0.60

POSITIVE LOGITS

 lift

1.07

 weights

1.01

 lifted

1.00

 lifting

1.00

 lifts

0.92

lift

0.88

hens

0.84

ĸļ

0.79

 tremend

0.79

weight

0.78

Activations Density 0.017%

phrases related to lifting or removing restrictions

terms related to lifting restrictions or bans

No Comments

No Known Activations