INDEX

Explanations

mentions of political resolutions or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to formal decisions or official statements, particularly highlighted by the use of the word "resolution" in various contexts

oai_token-act-pair · gpt-3.5-turbo Triggered by @danbraun

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

iott

-0.72

ocent

-0.72

rium

-0.70

pocket

-0.70

herty

-0.69

emade

-0.66

elong

-0.65

owler

-0.65

endon

-0.64

terson

-0.64

POSITIVE LOGITS

 resolutions

0.90

 resolution

0.88

 Resolution

0.87

mary

0.85

 authorizing

0.85

witz

0.74

xual

0.70

 resolves

0.70

ancing

0.67

 condemning

0.64

Activations Density 6.975%

mentions of political resolutions or decisions

terms related to formal decisions or official statements, particularly highlighted by the use of the word "resolution" in various contexts

No Comments

No Known Activations