INDEX

Explanations

specific locations or places mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations or geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

icer

-0.81

squ

-0.80

luaj

-0.78

vous

-0.78

igan

-0.77

uster

-0.74

tails

-0.74

sonian

-0.72

missions

-0.72

gres

-0.72

POSITIVE LOGITS

 location

0.99

 locations

0.99

 where

0.90

 locate

0.89

 nearest

0.85

 scout

0.82

 located

0.81

 vicinity

0.80

 coordinates

0.78

 near

0.76

Activations Density 0.057%

specific locations or places mentioned in the text

mentions of specific locations or geographical references

No Comments

No Known Activations