INDEX

Explanations

phrases or sentences indicating investigation or inquiry by authorities

oai_token-act-pair · gpt-3.5-turbo

phrases related to ongoing investigations

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

âĹ¼

-0.74

birth

-0.71

mpeg

-0.68

nown

-0.65

emonic

-0.62

Present

-0.62

hold

-0.61

pub

-0.60

rip

-0.60

perm

-0.60

POSITIVE LOGITS

 investigates

0.85

 investigating

0.84

 discl

0.82

 probing

0.75

 investigations

0.73

 investigation

0.73

 Probe

0.70

deen

0.69

 investigate

0.69

 magistrate

0.67

Activations Density 0.029%

phrases or sentences indicating investigation or inquiry by authorities

phrases related to ongoing investigations

No Comments

No Known Activations