INDEX

Explanations

words related to the name or abbreviation "Wo"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "wo" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

âĸ¬

-0.87

Magikarp

-0.81

IUM

-0.81

Interstitial

-0.79

ä»£

-0.75

 horizont

-0.72

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

-0.72

baugh

-0.72

ibly

-0.70

 Uriel

-0.70

POSITIVE LOGITS

ocom

1.04

ollen

0.97

ofer

0.95

zzi

0.95

onder

0.93

oster

0.93

jo

0.90

ogie

0.89

ollah

0.88

eful

0.88

Activations Density 0.026%

words related to the name or abbreviation "Wo"

occurrences of the word "wo" and its variations

No Comments

No Known Activations