INDEX

Explanations

terms related to negative emotions or displeasure

oai_token-act-pair · gpt-3.5-turbo

instances of the word "loathe" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rition

-0.80

glass

-0.78

pillar

-0.77

rity

-0.76

manship

-0.75

 Norn

-0.74

hower

-0.73

sonian

-0.70

ITAL

-0.69

lished

-0.68

POSITIVE LOGITS

aned

1.05

aning

1.04

oser

1.02

veland

0.99

aves

0.99

vers

0.89

ishly

0.89

ppy

0.88

ven

0.88

igh

0.87

Activations Density 0.010%

terms related to negative emotions or displeasure

instances of the word "loathe" and its variations

No Comments

No Known Activations