INDEX

Explanations

negations or phrases indicating the absence of something

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

New Auto-Interp

Configuration

jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

131,072

Data Type

torch.float32

Hook Name

blocks.0.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eers

-1.03

lace

-0.82

 Tags

-0.80

Developer

-0.78

eering

-0.77

iewicz

-0.74

 Turns

-0.74

 Inventory

-0.74

 Majesty

-0.72

 Specifications

-0.71

POSITIVE LOGITS

icably

1.03

©¶æ

0.93

etheless

0.92

 necessarily

0.86

 isot

0.85

ctica

0.84

 exha

0.84

icable

0.83

 contagious

0.80

 occas

0.79

Activations Density 0.359%

negations or phrases indicating the absence of something

No Comments

No Known Activations