INDEX

Explanations

phrases related to legal actions or court sentences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sentenced."

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

loo

-0.72

park

-0.70

walker

-0.69

aucus

-0.69

yip

-0.68

 Pegasus

-0.67

BLIC

-0.66

sie

-0.66

otin

-0.64

wer

-0.64

POSITIVE LOGITS

icts

1.16

 sentencing

1.00

 sentenced

0.98

 harshly

0.93

 sentences

0.90

 punishments

0.86

 sentence

0.82

 punishment

0.82

 inmates

0.82

 punished

0.81

Activations Density 0.016%

phrases related to legal actions or court sentences

occurrences of the word "sentenced."

No Comments

No Known Activations