INDEX

Explanations

names and dates in a specific format

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Takeru

-0.80

 Classification

-0.73

 Passage

-0.72

 Triangle

-0.69

 Perception

-0.66

 ACTION

-0.66

 accommodations

-0.66

 DIRECT

-0.65

 tampering

-0.65

 CONC

-0.65

POSITIVE LOGITS

atalie

0.81

ablo

0.81

fle

0.79

erk

0.78

ename

0.77

punk

0.75

eor

0.74

addon

0.74

official

0.73

arling

0.73

Activations Density 0.093%

names and dates in a specific format

mentions of specific individuals or entities

No Comments

No Known Activations