INDEX

Explanations

the word "that" followed by characteristic or descriptive elements

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endants

-0.93

osponsors

-0.93

okers

-0.86

osures

-0.86

pps

-0.86

amps

-0.85

sts

-0.84

asons

-0.84

anches

-0.84

bugs

-0.83

POSITIVE LOGITS

 uniqueness

1.06

 intangible

1.03

 newfound

1.03

 openness

1.03

 richness

1.02

 ambiguity

1.00

 totality

1.00

 knowledge

0.99

 momentum

0.99

 mindset

0.98

Activations Density 0.151%

the word "that" followed by characteristic or descriptive elements

the repetition of the word "that" in various contexts

No Comments

No Known Activations