INDEX

Explanations

words related to future events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "to" in various contexts

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

 millenn

-0.50

soDeliveryDate

-0.49

 disadvant

-0.45

listed

-0.45

_.

-0.45

 costing

-0.44

calling

-0.43

 packets

-0.43

typ

-0.42

soever

-0.42

POSITIVE LOGITS

 avoid

0.82

ggles

0.77

 accommodate

0.75

 relieve

0.75

pless

0.75

 maximize

0.75

 ensure

0.74

 compensate

0.74

 minimize

0.73

 achieve

0.73

Activations Density 0.575%

words related to future events

occurrences of the word "to" in various contexts

No Comments

No Known Activations