INDEX

Explanations

phrases related to generating content, revenue, or specific outcomes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nee

-0.87

hai

-0.83

mare

-0.78

say

-0.77

yer

-0.74

rock

-0.72

hid

-0.70

gerald

-0.68

phia

-0.68

bones

-0.67

POSITIVE LOGITS

 generate

0.88

 generators

0.86

kWh

0.83

 electricity

0.82

 revenue

0.81

 generates

0.80

 generated

0.78

 generating

0.78

 generator

0.75

assets

0.74

Activations Density 7.804%

phrases related to generating content, revenue, or specific outcomes

No Comments

No Known Activations