INDEX

Explanations

location descriptions, such as street names and types of establishments like auto dealerships

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or movements associated with events

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

 Replay

-0.65

pires

-0.64

"},"

-0.63

 historically

-0.61

 regimes

-0.61

zbollah

-0.58

)?

-0.58

 depends

-0.57

 inherently

-0.57

 millennial

-0.55

POSITIVE LOGITS

—"

0.84

Newsletter

0.76

quit

0.65

agent

0.64

—-

0.63

igslist

0.62

 glim

0.59

EH

0.59

 assum

0.58

Advertisement

0.58

Activations Density 1.225%

location descriptions, such as street names and types of establishments like auto dealerships

references to specific locations or movements associated with events

No Comments

No Known Activations