INDEX

Explanations

terms related to institutions, especially higher education institutions

oai_token-act-pair · gpt-3.5-turbo

references to institutions, particularly their roles and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rockies

-0.74

hner

-0.70

storms

-0.69

gets

-0.68

 Powder

-0.68

THER

-0.66

atche

-0.66

ioxide

-0.62

ulf

-0.62

hab

-0.62

POSITIVE LOGITS

itutional

1.08

 institution

0.96

arians

0.92

 institutions

0.91

 Institution

0.89

ally

0.86

ually

0.86

utions

0.84

ional

0.78

opathic

0.74

Activations Density 0.021%

terms related to institutions, especially higher education institutions

references to institutions, particularly their roles and characteristics

No Comments

No Known Activations