INDEX

Explanations

phrases related to provocation or providing evidence

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of provocation or provocation-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Rite

-0.71

Pie

-0.70

 Eclipse

-0.68

mare

-0.65

 Lobby

-0.64

geist

-0.64

Lay

-0.62

morph

-0.62

 Masters

-0.61

 Scotch

-0.61

POSITIVE LOGITS

 prov

1.13

idence

1.06

idently

1.04

idential

1.01

uitous

1.01

idences

1.01

ably

0.92

isec

0.88

irus

0.86

iso

0.86

Activations Density 0.006%

phrases related to provocation or providing evidence

words related to the concept of provocation or provocation-related contexts

No Comments

No Known Activations