INDEX

Explanations

words related to rumors

oai_token-act-pair · gpt-3.5-turbo

discussions and mentions of rumors

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

ells

-0.81

artney

-0.77

 Lonely

-0.68

alone

-0.66

tein

-0.65

ĸļ

-0.65

acted

-0.65

hematic

-0.64

asper

-0.64

olly

-0.64

POSITIVE LOGITS

 rumor

1.15

 rumors

1.11

 rumours

0.97

Rum

0.92

 indu

0.89

 gossip

0.84

Rum

0.82

 rumored

0.82

 speculation

0.78

 leak

0.76

Activations Density 0.026%

words related to rumors

discussions and mentions of rumors

No Comments

No Known Activations