INDEX

Explanations

solutions to various problems or issues being discussed within a context

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

prints

-0.84

avia

-0.79

 livest

-0.77

rob

-0.76

head

-0.75

arlane

-0.74

ensen

-0.73

nih

-0.72

wood

-0.72

ardy

-0.72

POSITIVE LOGITS

 solve

0.85

 solutions

0.83

olution

0.83

 thereto

0.83

 solution

0.82

vable

0.80

olutions

0.79

Solution

0.77

 solving

0.77

[+]

0.71

Activations Density 5.380%

solutions to various problems or issues being discussed within a context

No Comments

No Known Activations