INDEX

Explanations

urging or encouraging actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

terms related to requests or calls to action

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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.75

çĦ

-0.72

ìĿ

-0.64

nown

-0.63

bourne

-0.63

anuts

-0.62

Interstitial

-0.61

LP

-0.61

 Alone

-0.60

miah

-0.58

POSITIVE LOGITS

 caution

1.07

 forgiveness

0.84

 patience

0.82

 electors

0.79

 restraint

0.78

us

0.77

ourage

0.76

 reconsider

0.76

 travellers

0.74

 vigilance

0.72

Activations Density 0.039%

urging or encouraging actions or behaviors

terms related to requests or calls to action

No Comments

No Known Activations