INDEX

Explanations

terms of "followed by."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "followed" to indicate sequential relationships or events

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

pite

-0.79

pmwiki

-0.70

inese

-0.67

negie

-0.65

cit

-0.65

vere

-0.65

borgh

-0.64

anyon

-0.64

mud

-0.62

bent

-0.62

POSITIVE LOGITS

ĸļ

0.91

 closely

0.89

 followed

0.82

 suit

0.79

 follows

0.76

 follow

0.73

 thereafter

0.69

 faithfully

0.68

 rollout

0.66

 Follow

0.65

Activations Density 0.027%

terms of "followed by."

instances of the word "followed" to indicate sequential relationships or events

No Comments

No Known Activations