INDEX

Explanations

words related to geographical locations and people's names

oai_token-act-pair · gpt-3.5-turbo

words related to geographical locations or urban settings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kefeller

-0.69

perty

-0.67

STON

-0.65

itable

-0.64

 Bots

-0.60

PER

-0.59

ishable

-0.59

dylib

-0.58

ptions

-0.58

pton

-0.56

POSITIVE LOGITS

oday

1.15

ainment

1.13

rophe

1.11

ronics

1.10

ypes

1.07

ropy

1.07

opia

1.07

rop

1.05

hetics

1.05

rition

1.05

Activations Density 0.216%

words related to geographical locations and people's names

words related to geographical locations or urban settings

No Comments

No Known Activations