INDEX

Explanations

references to governmental actions or decisions related to legal or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Instruments

-0.70

idth

-0.70

 Digest

-0.65

 Nano

-0.65

 Angry

-0.64

 Confeder

-0.60

 Admir

-0.59

 Fine

-0.58

 Politics

-0.57

fuck

-0.57

POSITIVE LOGITS

alian

1.18

self

1.18

chy

1.05

atically

0.95

atic

0.93

unes

0.89

selves

0.86

asca

0.78

ELF

0.77

 squarely

0.77

Activations Density 0.116%

references to governmental actions or decisions related to legal or political contexts

No Comments

No Known Activations