INDEX

Explanations

numerical values within a specific context

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 unden

-0.59

 trave

-0.56

inventoryQuantity

-0.55

ortunately

-0.51

 enthusi

-0.51

 exting

-0.50

 behavi

-0.50

 neighb

-0.50

 disg

-0.49

 conflic

-0.49

POSITIVE LOGITS

1.10

1.09

1.08

1.07

Activations Density 0.560%

numerical values within a specific context

numerical data or statistics in the text

No Comments

No Known Activations