INDEX

Explanations

words related to pursuing goals or interests

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pursue" 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 @ 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

electric

-0.69

ombo

-0.68

lua

-0.65

board

-0.63

ailand

-0.62

oxy

-0.62

finger

-0.62

cious

-0.61

 arsen

-0.61

immer

-0.61

POSITIVE LOGITS

 pursued

0.95

 pursue

0.93

ments

0.90

TAIN

0.84

iveness

0.84

 pursuing

0.83

iage

0.83

 avenues

0.80

ively

0.76

anced

0.75

Activations Density 0.021%

words related to pursuing goals or interests

instances of the word "pursue" and its variations

No Comments

No Known Activations