INDEX

Explanations

words related to the gradual development or progression of events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "unfold" and its variations, indicating developments or events in progress

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

uana

-0.78

iked

-0.77

alty

-0.76

ondo

-0.72

unte

-0.72

ogun

-0.71

este

-0.69

chens

-0.69

exc

-0.68

ogo

-0.64

POSITIVE LOGITS

 unfold

1.31

 unfolding

1.21

 unfolded

1.15

 unfolds

1.08

ĸļ

0.85

 Afric

0.82

URES

0.81

 anew

0.79

 Tanz

0.75

 unravel

0.72

Activations Density 0.028%

words related to the gradual development or progression of events

occurrences of the word "unfold" and its variations, indicating developments or events in progress

No Comments

No Known Activations