INDEX

Explanations

instances of the word 'third'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "third."

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

++++++++++++++++

-0.89

staking

-0.83

immers

-0.75

Money

-0.70

UTION

-0.70

Reward

-0.69

BUS

-0.69

Tokens

-0.68

ITED

-0.68

Quantity

-0.67

POSITIVE LOGITS

rd

1.09

 baseman

1.06

 quarters

0.86

 inning

0.82

irty

0.79

ousand

0.76

ortun

0.75

orne

0.75

 consecutive

0.74

 dimensional

0.72

Activations Density 0.033%

instances of the word 'third'

occurrences of the term "third."

No Comments

No Known Activations