INDEX

Explanations

phrases containing the word "common"

oai_token-act-pair · gpt-3.5-turbo

the frequency of certain issues or phenomena described as "common."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mosp

-0.84

overe

-0.77

resy

-0.75

otos

-0.73

enda

-0.73

usalem

-0.73

forestation

-0.72

otiation

-0.70

ternity

-0.69

atever

-0.69

POSITIVE LOGITS

wealth

1.17

alities

1.02

 occurrences

1.00

 occurrence

0.96

places

0.94

 denomin

0.89

ality

0.87

 ancestor

0.87

ensical

0.82

ãĥ¬

0.76

Activations Density 0.018%

phrases containing the word "common"

the frequency of certain issues or phenomena described as "common."

No Comments

No Known Activations