INDEX

Explanations

words related to actions and interactions between people or about specific situations

oai_token-act-pair · gpt-3.5-turbo

specific non-lexical characters or symbols used in dialogue or narration

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 usefulness

-0.86

 decentral

-0.85

 merits

-0.83

 ecosystem

-0.82

 democracies

-0.82

 benefits

-0.81

 partnerships

-0.81

 neutrality

-0.81

 sustainability

-0.80

 diversity

-0.80

POSITIVE LOGITS

then

1.18

she

1.10

him

1.05

later

1.04

his

1.02

Then

1.02

Later

0.98

laugh

0.97

Suddenly

0.97

said

0.93

Activations Density 0.343%

words related to actions and interactions between people or about specific situations

specific non-lexical characters or symbols used in dialogue or narration

No Comments

No Known Activations