INDEX

Explanations

information about events or actions planned for the future

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "be" 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 @ 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

 Dresden

-0.71

 sqor

-0.69

ileaks

-0.63

 fray

-0.62

 srfAttach

-0.62

 Franch

-0.62

iasco

-0.61

 Prescott

-0.61

terday

-0.60

fig

-0.59

POSITIVE LOGITS

 able

1.09

fits

0.96

fitting

0.95

fit

0.95

arers

0.94

heading

0.93

 replaced

0.91

ige

0.91

 seen

0.90

leeve

0.90

Activations Density 0.100%

information about events or actions planned for the future

occurrences of the verb "be" in various contexts

No Comments

No Known Activations